初始化项目，由ModelHub XC社区提供模型
Model: h2oai/h2ogpt-4096-llama2-70b Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
126
LICENSE.txt
Normal file
126
LICENSE.txt
Normal file
@@ -0,0 +1,126 @@
|
||||
LLAMA 2 COMMUNITY LICENSE AGREEMENT
|
||||
Llama 2 Version Release Date: July 18, 2023
|
||||
|
||||
"Agreement" means the terms and conditions for use, reproduction, distribution and
|
||||
modification of the Llama Materials set forth herein.
|
||||
|
||||
"Documentation" means the specifications, manuals and documentation
|
||||
accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
|
||||
libraries/llama-downloads/.
|
||||
|
||||
"Licensee" or "you" means you, or your employer or any other person or entity (if
|
||||
you are entering into this Agreement on such person or entity's behalf), of the age
|
||||
required under applicable laws, rules or regulations to provide legal consent and that
|
||||
has legal authority to bind your employer or such other person or entity if you are
|
||||
entering in this Agreement on their behalf.
|
||||
|
||||
"Llama 2" means the foundational large language models and software and
|
||||
algorithms, including machine-learning model code, trained model weights,
|
||||
inference-enabling code, training-enabling code, fine-tuning enabling code and other
|
||||
elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
|
||||
libraries/llama-downloads/.
|
||||
|
||||
"Llama Materials" means, collectively, Meta's proprietary Llama 2 and
|
||||
Documentation (and any portion thereof) made available under this Agreement.
|
||||
|
||||
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
|
||||
are an entity, your principal place of business is in the EEA or Switzerland) and Meta
|
||||
Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
||||
|
||||
By clicking "I Accept" below or by using or distributing any portion or element of the
|
||||
Llama Materials, you agree to be bound by this Agreement.
|
||||
|
||||
1. License Rights and Redistribution.
|
||||
|
||||
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
|
||||
transferable and royalty-free limited license under Meta's intellectual property or
|
||||
other rights owned by Meta embodied in the Llama Materials to use, reproduce,
|
||||
distribute, copy, create derivative works of, and make modifications to the Llama
|
||||
Materials.
|
||||
|
||||
b. Redistribution and Use.
|
||||
|
||||
i. If you distribute or make the Llama Materials, or any derivative works
|
||||
thereof, available to a third party, you shall provide a copy of this Agreement to such
|
||||
third party.
|
||||
ii. If you receive Llama Materials, or any derivative works thereof, from
|
||||
a Licensee as part of an integrated end user product, then Section 2 of this
|
||||
Agreement will not apply to you.
|
||||
|
||||
iii. You must retain in all copies of the Llama Materials that you
|
||||
distribute the following attribution notice within a "Notice" text file distributed as a
|
||||
part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
|
||||
Copyright (c) Meta Platforms, Inc. All Rights Reserved."
|
||||
|
||||
iv. Your use of the Llama Materials must comply with applicable laws
|
||||
and regulations (including trade compliance laws and regulations) and adhere to the
|
||||
Acceptable Use Policy for the Llama Materials (available at
|
||||
https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
|
||||
this Agreement.
|
||||
|
||||
v. You will not use the Llama Materials or any output or results of the
|
||||
Llama Materials to improve any other large language model (excluding Llama 2 or
|
||||
derivative works thereof).
|
||||
|
||||
2. Additional Commercial Terms. If, on the Llama 2 version release date, the
|
||||
monthly active users of the products or services made available by or for Licensee,
|
||||
or Licensee's affiliates, is greater than 700 million monthly active users in the
|
||||
preceding calendar month, you must request a license from Meta, which Meta may
|
||||
grant to you in its sole discretion, and you are not authorized to exercise any of the
|
||||
rights under this Agreement unless or until Meta otherwise expressly grants you
|
||||
such rights.
|
||||
|
||||
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
|
||||
LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
|
||||
PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
|
||||
EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
|
||||
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
|
||||
FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
|
||||
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
|
||||
THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
|
||||
USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||
|
||||
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
|
||||
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
|
||||
NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
|
||||
AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
|
||||
CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
|
||||
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
|
||||
ANY OF THE FOREGOING.
|
||||
|
||||
5. Intellectual Property.
|
||||
|
||||
a. No trademark licenses are granted under this Agreement, and in
|
||||
connection with the Llama Materials, neither Meta nor Licensee may use any name
|
||||
or mark owned by or associated with the other or any of its affiliates, except as
|
||||
required for reasonable and customary use in describing and redistributing the
|
||||
Llama Materials.
|
||||
|
||||
b. Subject to Meta's ownership of Llama Materials and derivatives made by or
|
||||
for Meta, with respect to any derivative works and modifications of the Llama
|
||||
Materials that are made by you, as between you and Meta, you are and will be the
|
||||
owner of such derivative works and modifications.
|
||||
|
||||
c. If you institute litigation or other proceedings against Meta or any entity
|
||||
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
|
||||
Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
|
||||
constitutes infringement of intellectual property or other rights owned or licensable
|
||||
by you, then any licenses granted to you under this Agreement shall terminate as of
|
||||
the date such litigation or claim is filed or instituted. You will indemnify and hold
|
||||
harmless Meta from and against any claim by any third party arising out of or related
|
||||
to your use or distribution of the Llama Materials.
|
||||
|
||||
6. Term and Termination. The term of this Agreement will commence upon your
|
||||
acceptance of this Agreement or access to the Llama Materials and will continue in
|
||||
full force and effect until terminated in accordance with the terms and conditions
|
||||
herein. Meta may terminate this Agreement if you are in breach of any term or
|
||||
condition of this Agreement. Upon termination of this Agreement, you shall delete
|
||||
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
|
||||
termination of this Agreement.
|
||||
|
||||
7. Governing Law and Jurisdiction. This Agreement will be governed and
|
||||
construed under the laws of the State of California without regard to choice of law
|
||||
principles, and the UN Convention on Contracts for the International Sale of Goods
|
||||
does not apply to this Agreement. The courts of California shall have exclusive
|
||||
jurisdiction of any dispute arising out of this Agreement.
|
||||
|
||||
55
README.md
Normal file
55
README.md
Normal file
@@ -0,0 +1,55 @@
|
||||
---
|
||||
inference: false
|
||||
language:
|
||||
- en
|
||||
license: llama2
|
||||
model_type: llama
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- facebook
|
||||
- meta
|
||||
- pytorch
|
||||
- llama
|
||||
- llama-2
|
||||
- h2ogpt
|
||||
---
|
||||
|
||||
h2oGPT clone of [Meta's Llama 2 70B](https://huggingface.co/meta-llama/Llama-2-70b-hf).
|
||||
|
||||
This model can be fine-tuned with [H2O.ai](https://h2o.ai/) open-source software:
|
||||
- h2oGPT https://github.com/h2oai/h2ogpt/
|
||||
- H2O LLM Studio https://h2o.ai/platform/ai-cloud/make/llm-studio/
|
||||
|
||||
Try our live [h2oGPT demo](https://gpt.h2o.ai) with side-by-side LLM comparisons and private document chat!
|
||||
|
||||
|
||||
## Model Architecture
|
||||
|
||||
```
|
||||
LlamaForCausalLM(
|
||||
(model): LlamaModel(
|
||||
(embed_tokens): Embedding(32000, 8192, padding_idx=0)
|
||||
(layers): ModuleList(
|
||||
(0-79): 80 x LlamaDecoderLayer(
|
||||
(self_attn): LlamaAttention(
|
||||
(q_proj): Linear4bit(in_features=8192, out_features=8192, bias=False)
|
||||
(k_proj): Linear4bit(in_features=8192, out_features=1024, bias=False)
|
||||
(v_proj): Linear4bit(in_features=8192, out_features=1024, bias=False)
|
||||
(o_proj): Linear4bit(in_features=8192, out_features=8192, bias=False)
|
||||
(rotary_emb): LlamaRotaryEmbedding()
|
||||
)
|
||||
(mlp): LlamaMLP(
|
||||
(gate_proj): Linear4bit(in_features=8192, out_features=28672, bias=False)
|
||||
(up_proj): Linear4bit(in_features=8192, out_features=28672, bias=False)
|
||||
(down_proj): Linear4bit(in_features=28672, out_features=8192, bias=False)
|
||||
(act_fn): SiLUActivation()
|
||||
)
|
||||
(input_layernorm): LlamaRMSNorm()
|
||||
(post_attention_layernorm): LlamaRMSNorm()
|
||||
)
|
||||
)
|
||||
(norm): LlamaRMSNorm()
|
||||
)
|
||||
(lm_head): Linear(in_features=8192, out_features=32000, bias=False)
|
||||
)
|
||||
```
|
||||
3
Responsible-Use-Guide.pdf
Normal file
3
Responsible-Use-Guide.pdf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:525dc349d71fe257fce4098c146446df6fef4247174f351381e4c3214af126f0
|
||||
size 1253223
|
||||
50
USE_POLICY.md
Normal file
50
USE_POLICY.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# Llama 2 Acceptable Use Policy
|
||||
|
||||
Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
|
||||
|
||||
## Prohibited Uses
|
||||
We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to:
|
||||
|
||||
1. Violate the law or others’ rights, including to:
|
||||
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
|
||||
1. Violence or terrorism
|
||||
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
|
||||
3. Human trafficking, exploitation, and sexual violence
|
||||
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
|
||||
5. Sexual solicitation
|
||||
6. Any other criminal activity
|
||||
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
|
||||
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
|
||||
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
|
||||
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
|
||||
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
|
||||
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
|
||||
|
||||
|
||||
|
||||
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
|
||||
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
|
||||
2. Guns and illegal weapons (including weapon development)
|
||||
3. Illegal drugs and regulated/controlled substances
|
||||
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
|
||||
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
|
||||
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
|
||||
|
||||
|
||||
|
||||
3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
|
||||
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
|
||||
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
|
||||
3. Generating, promoting, or further distributing spam
|
||||
4. Impersonating another individual without consent, authorization, or legal right
|
||||
5. Representing that the use of Llama 2 or outputs are human-generated
|
||||
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
|
||||
4. Fail to appropriately disclose to end users any known dangers of your AI system
|
||||
|
||||
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
|
||||
|
||||
* Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
|
||||
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
|
||||
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
|
||||
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)
|
||||
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "h2oai/h2ogpt-4096-llama2-70b",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 8192,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 28672,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 80,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.32.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"max_length": 4096,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.32.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00015.safetensors
Normal file
3
model-00001-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:61c65a110ea6889876787b38160158204fdbc8b654e169de1fb41c214d95a661
|
||||
size 9852591960
|
||||
3
model-00002-of-00015.safetensors
Normal file
3
model-00002-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd2bc67e6f4c202277bffdb23b1fe149dd007ddd4c69805c56cb611396f12d28
|
||||
size 9798099016
|
||||
3
model-00003-of-00015.safetensors
Normal file
3
model-00003-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:73b7013d32a2b10e4382550778d8db420bb5bd91eb14ec49b4beb06e570fb09c
|
||||
size 9965870512
|
||||
3
model-00004-of-00015.safetensors
Normal file
3
model-00004-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45b24dd4b03221c5dbf1da22a4c65ed5099de5d53c313ff9bb9476c5f9d14a6e
|
||||
size 9798066064
|
||||
3
model-00005-of-00015.safetensors
Normal file
3
model-00005-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4221301ea892eec7fc33a01c24a58bd0a2330d9d74e2f333ac09645eb28f9e7a
|
||||
size 9798099056
|
||||
3
model-00006-of-00015.safetensors
Normal file
3
model-00006-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4fb1dbbb634cb963ad3e99bb3d2a8a6d2aecf41e1120e1c125ced8ce3825ab0
|
||||
size 9798099056
|
||||
3
model-00007-of-00015.safetensors
Normal file
3
model-00007-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a516e201780faa4aca55f61ba3bf159350f6a445c7c4e6043a7011fa250abbd0
|
||||
size 9965870512
|
||||
3
model-00008-of-00015.safetensors
Normal file
3
model-00008-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d0496e32a1a58d702c4b69a72e5793cdcd8e4bc1b80fdca7cf724039f4a2f66
|
||||
size 9798066064
|
||||
3
model-00009-of-00015.safetensors
Normal file
3
model-00009-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2fd9f84a743413035bdc8ec8ea6569306c12b78451659353fb8bb784690d64d
|
||||
size 9798099056
|
||||
3
model-00010-of-00015.safetensors
Normal file
3
model-00010-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c0265d4d14fad570df6651d874e3717047110730630ce136ff9e442e216f1cd8
|
||||
size 9798099056
|
||||
3
model-00011-of-00015.safetensors
Normal file
3
model-00011-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:49b9e7b2f75cb12ff26e72e8ba7f841c3a2125059b04f91c994c63f80107c220
|
||||
size 9965870512
|
||||
3
model-00012-of-00015.safetensors
Normal file
3
model-00012-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dc3ce7c3220e6b86545438126d2bfc091402c8d557631aa75e71902cf71bd5bb
|
||||
size 9798066064
|
||||
3
model-00013-of-00015.safetensors
Normal file
3
model-00013-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c4ce7127d4facdf06a57fdd2d2527c2a727d5c5f6190f2686943d89f936fc9e
|
||||
size 9798099056
|
||||
3
model-00014-of-00015.safetensors
Normal file
3
model-00014-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:642989aef716c4e2ee53d7b4effc77972a860ef33f08a8fce7eb2bda2495b86f
|
||||
size 9496124816
|
||||
3
model-00015-of-00015.safetensors
Normal file
3
model-00015-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9eb0e16b04caf90da13be6c1acedbdd1f4940b4ba1d2c7f8bbbc5e7091d9c053
|
||||
size 524288128
|
||||
810
model.safetensors.index.json
Normal file
810
model.safetensors.index.json
Normal file
@@ -0,0 +1,810 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 137953316864
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00015-of-00015.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.66.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.67.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
|
||||
"model.layers.68.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.71.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.72.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.73.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
|
||||
"model.layers.74.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
|
||||
"model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
|
||||
"model.layers.76.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
|
||||
"model.layers.77.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
|
||||
"model.layers.78.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
|
||||
"model.layers.79.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.norm.weight": "model-00014-of-00015.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b1ca21f51322b45ecb26d2a0634c7c7093a7919f6b5ca35a02357bb401802954
|
||||
size 9852605685
|
||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:185b8f973f862a0c87982af06c93312639877646e6f089ccd087e4ddeb98b6b3
|
||||
size 9798113337
|
||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:36c70a1e65725bcac8c99695afca628268450c03a012b5f7f0fb6a5bcd9ec4ea
|
||||
size 9965883861
|
||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c39b6f0e3b9f0605fadb48ca2cb2c5cf35f5950538df156ef0a313adff426f5
|
||||
size 9798079785
|
||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:309c5bd52fd4080b919f36543d616a675c5bce56cbbca61a203ce05a9e454e18
|
||||
size 9798113313
|
||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75550779ee1782f0f0c165ce61b90b352bc9468c57ed4dddf0dc5ef29f677c01
|
||||
size 9798113337
|
||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3f5c3ee1e888712cfb3670a85ce8b474c2e38b3ce6a30ed13230b5fa0201584
|
||||
size 9965883861
|
||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0450bf1a29101ae2a228616ead1ac707852ec38996b215c225fe189241397b70
|
||||
size 9798079785
|
||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1dd108efa10d308c86f857acbce334907de12022feb8b2a1042874cf0195c1d7
|
||||
size 9798113313
|
||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ac668f45a2f7526ed2ff034b979c4e496db3e8044dad4d0e7a7b1bcabbd772b
|
||||
size 9798113337
|
||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a99337a64550478d74f01b7f118e931e253303a2f929f4825281d44a0d8c6b79
|
||||
size 9965883861
|
||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3e7b6ab2fa1560c461d8d34befa1a05f9c6dc64614e628e19d98df496049b29
|
||||
size 9798079785
|
||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:216b4cd902263eb151b1a7a201d58337c91bd463056e5dc2d51e8d67db1a39f9
|
||||
size 9798113313
|
||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4d574d7105753347709599589fe7e92df1f9a2827d345ff5a88c79781928b306
|
||||
size 9496138113
|
||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b6ffbe784f638a0e4e258fa6c252554ff96e486b20a18b4ba05de5cc693f86e
|
||||
size 524288938
|
||||
810
pytorch_model.bin.index.json
Normal file
810
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,810 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 137953316864
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user