初始化项目，由ModelHub XC社区提供模型
Model: IQuestLab/Fleming-R1-32B Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
images/exp_result.png filter=lfs diff=lfs merge=lfs -text
|
||||
images/size_compare.png filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
202
LICENSE
Normal file
202
LICENSE
Normal file
@@ -0,0 +1,202 @@
|
||||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright 2024 Alibaba Cloud
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
126
README.md
Normal file
126
README.md
Normal file
@@ -0,0 +1,126 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
license_link: https://huggingface.co/UbiquantAI/Fleming-R1-32B/blob/main/LICENSE
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Fleming-R1-32B
|
||||
<p align="center" style="margin: 0;">
|
||||
<a href="https://github.com/UbiquantAI/Fleming-R1" aria-label="GitHub Repository" style="text-decoration:none;">
|
||||
<span style="display:inline-flex;align-items:center;gap:.35em;">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16"
|
||||
width="16" height="16" aria-hidden="true"
|
||||
style="vertical-align:text-bottom;fill:currentColor;">
|
||||
<path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8Z"/>
|
||||
</svg>
|
||||
<span>GitHub</span>
|
||||
</span>
|
||||
</a>
|
||||
<span style="margin:0 .75em;opacity:.6;">•</span>
|
||||
<a href="https://arxiv.org/abs/2509.15279" aria-label="Paper">📑 Paper</a>
|
||||
</p>
|
||||
|
||||
## Highlights
|
||||
|
||||
## 📖 Model Overview
|
||||
|
||||
Fleming-R1 is a reasoning model for medical scenarios that can perform step-by-step analysis of complex problems and produce reliable answers. The model follows a training paradigm of “chain-of-thought cold start” plus large-scale reinforcement learning. On multiple medical benchmarks, the 7B version achieves SOTA among models of a similar size; the 32B version performs close to the much larger GPT-OSS-120B and shows stronger results on Chinese tasks.
|
||||
|
||||
**Model Features:**
|
||||
|
||||
* **Reasoning-oriented data strategy** Combines public medical datasets with knowledge graphs to improve coverage of rare diseases, medications, and multi-hop reasoning chains;
|
||||
* **Chain-of-thought cold start** Uses high-quality reasoning traces distilled from teacher models to guide the model in learning basic reasoning patterns;
|
||||
* **Two-stage reinforcement learning** Employs adaptive hard-negative mining to strengthen the model’s reasoning when facing difficult problems.
|
||||
|
||||
## 📦 Releases
|
||||
|
||||
- **Fleming-R1-7B** —— Trained on Qwen2.5-7B
|
||||
🤗 [`UbiquantAI/Fleming-R1-7B`](https://huggingface.co/UbiquantAI/Fleming-R1-7B)
|
||||
- **Fleming-R1-32B** —— Trained on Qwen3-32B
|
||||
🤗 [`UbiquantAI/Fleming-R1-32B`](https://huggingface.co/UbiquantAI/Fleming-R1-32B)
|
||||
|
||||
## 📊 Performance
|
||||
|
||||
### Main Benchmark Results
|
||||
|
||||
<div align="center">
|
||||
<img src="images/exp_result.png" alt="Benchmark Results" width="60%">
|
||||
</div>
|
||||
|
||||
### Reasoning Ability Comparison
|
||||
|
||||
On the MedXpertQA benchmark, which evaluates medical reasoning ability, Fleming-R1 surpasses models of similar—and even larger—sizes, and is on par with certain closed-source models.
|
||||
|
||||
<div align="center">
|
||||
<img src="images/size_compare.png" alt="Size comparison" width="60%">
|
||||
</div>
|
||||
|
||||
## 🔧 Quick Start
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "UbiquantAI/Fleming-R1-32B"
|
||||
|
||||
# load the tokenizer and the model
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="auto",
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
# prepare the model input
|
||||
prompt = "What should I do if I suddenly develop a fever?"
|
||||
messages = [
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
|
||||
# conduct text completion
|
||||
generated_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_new_tokens=32768
|
||||
)
|
||||
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
||||
|
||||
# parsing thinking content
|
||||
try:
|
||||
# rindex finding 151668 (</think>)
|
||||
index = len(output_ids) - output_ids[::-1].index(151668)
|
||||
except ValueError:
|
||||
index = 0
|
||||
|
||||
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
|
||||
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
|
||||
|
||||
print("thinking content:", thinking_content)
|
||||
print("content:", content)
|
||||
|
||||
```
|
||||
|
||||
## ⚠️ Safety Statement
|
||||
|
||||
This project is for research and non-clinical reference only; it must not be used for actual diagnosis or treatment decisions.
|
||||
The generated reasoning traces are an auditable intermediate process and do not constitute medical advice.
|
||||
In medical scenarios, results must be reviewed and approved by qualified professionals, and all applicable laws, regulations, and privacy compliance requirements in your region must be followed.
|
||||
|
||||
## 📚 Citation
|
||||
|
||||
```bibtex
|
||||
@misc{flemingr1,
|
||||
title={Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning},
|
||||
author={Chi Liu and Derek Li and Yan Shu and Robin Chen and Derek Duan and Teng Fang and Bryan Dai},
|
||||
year={2025},
|
||||
eprint={2509.15279},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2509.15279},
|
||||
}
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 25600,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 64,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.1"
|
||||
}
|
||||
3
images/exp_result.png
Normal file
3
images/exp_result.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a0c09daef7cc552d1b0c39ddc8165abd9c7d967807f3d070790dc9f881f621b6
|
||||
size 163888
|
||||
3
images/size_compare.png
Normal file
3
images/size_compare.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e292c99dce9c02be1317dc7b87aa261803a298e5825062f4426db5b5a348541
|
||||
size 150557
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00014.safetensors
Normal file
3
model-00001-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6880e4d742a14617f8f9562ad3f4ec9f2e525ecd017b0bf21725df78740ec805
|
||||
size 4886496696
|
||||
3
model-00002-of-00014.safetensors
Normal file
3
model-00002-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db51fec651cb4a560233dce25cce08b8d11528e12daa4da5ba4c733d2a16d1ec
|
||||
size 4970412856
|
||||
3
model-00003-of-00014.safetensors
Normal file
3
model-00003-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9f8db332c5922737894fc107242d7463fa30c9503c7f690d3c749e441c4e69b
|
||||
size 4991322856
|
||||
3
model-00004-of-00014.safetensors
Normal file
3
model-00004-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd13822aca88aaccf171ab284296cfb2d36f292eea26e5e30bde7ec7dcdb3328
|
||||
size 4802631888
|
||||
3
model-00005-of-00014.safetensors
Normal file
3
model-00005-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:91178ffa772f9af8259938d6cb7373077c503a98f301eb7ecbd6f17852db49cc
|
||||
size 4917943592
|
||||
3
model-00006-of-00014.safetensors
Normal file
3
model-00006-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6a6412694ac40aa3870c46947b645ca28f074d9e701c40511cf8bcd7a9c46330
|
||||
size 4750182192
|
||||
3
model-00007-of-00014.safetensors
Normal file
3
model-00007-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f50e1c1c0a8ac5a036103ef0585894458270350e6e031bef38daa08c3386dbf3
|
||||
size 4760614808
|
||||
3
model-00008-of-00014.safetensors
Normal file
3
model-00008-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7c3f4f3195a5a237a10378a5cf39227a939bd7f2036cbe6cc14f9c10e92d06e
|
||||
size 3953231800
|
||||
3
model-00009-of-00014.safetensors
Normal file
3
model-00009-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50e8551c3d116c4a743f07d2192f0a2e77718d18ae6283e9d424765e30c5ad5f
|
||||
size 4869412672
|
||||
3
model-00010-of-00014.safetensors
Normal file
3
model-00010-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f6ac0fa035b5ff65d93ac66aeb18d0867c8a0e956f4a66262171243d135901e
|
||||
size 4764544848
|
||||
3
model-00011-of-00014.safetensors
Normal file
3
model-00011-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b4a3e6f796649f465ff714743affb3275a17c1b9477bcdfbed50486b78c7e6f
|
||||
size 4970371432
|
||||
3
model-00012-of-00014.safetensors
Normal file
3
model-00012-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6fc0908a7e0d237e70993593eb45dee4918d5d45ef5fd3b48f68da3589fd8cc7
|
||||
size 4792061008
|
||||
3
model-00013-of-00014.safetensors
Normal file
3
model-00013-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6dd9b584ead9d90d8a4f99d1cb22777be1f9601699328f1a9847ffc8e5706ef1
|
||||
size 4771079640
|
||||
3
model-00014-of-00014.safetensors
Normal file
3
model-00014-of-00014.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:85afab4387493d1928b59bca2efe31a0e795fc7bde73c0d7c0251c62ebba5058
|
||||
size 3324022120
|
||||
714
model.safetensors.index.json
Normal file
714
model.safetensors.index.json
Normal file
@@ -0,0 +1,714 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 65524246528
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00009-of-00014.safetensors",
|
||||
"model.embed_tokens.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00014.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user