初始化项目，由ModelHub XC社区提供模型
Model: unsloth/Llama-Guard-4-12B Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
32
LICENSE
Normal file
32
LICENSE
Normal file
@@ -0,0 +1,32 @@
|
||||
LLAMA 4 COMMUNITY LICENSE AGREEMENT
|
||||
Llama 4 Version Effective Date: April 5, 2025
|
||||
|
||||
“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
|
||||
“Documentation” means the specifications, manuals and documentation accompanying Llama 4 distributed by Meta at https://www.llama.com/docs/overview.
|
||||
“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
|
||||
“Llama 4” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads.
|
||||
“Llama Materials” means, collectively, Meta’s proprietary Llama 4 and Documentation (and any portion thereof) made available under this Agreement.
|
||||
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
||||
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
|
||||
|
||||
1. License Rights and Redistribution.
|
||||
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty- free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
|
||||
b. Redistribution and Use.
|
||||
i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.
|
||||
|
||||
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
|
||||
|
||||
iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 4 is licensed under the Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
|
||||
|
||||
iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.com/llama4/use-policy), which is hereby incorporated by reference into this Agreement.
|
||||
2. Additional Commercial Terms. If, on the Llama 4 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
|
||||
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
|
||||
5. Intellectual Property.
|
||||
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
|
||||
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
|
||||
|
||||
c. If you institute litigation or other proceedings against Meta or any entity (including a cross- claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 4 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
|
||||
|
||||
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
|
||||
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.
|
||||
47
README.md
Normal file
47
README.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
license: Apache License 2.0
|
||||
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
---
|
||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
||||
|
||||
SDK下载
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
```
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('unsloth/Llama-Guard-4-12B')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/unsloth/Llama-Guard-4-12B.git
|
||||
```
|
||||
|
||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
||||
78
USE_POLICY.md
Normal file
78
USE_POLICY.md
Normal file
@@ -0,0 +1,78 @@
|
||||
**Llama 4** **Acceptable Use Policy**
|
||||
|
||||
Meta is committed to promoting safe and fair use of its tools and features, including Llama 4. If you access or use Llama 4, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [https://www.llama.com/llama4/use-policy](https://www.llama.com/llama4/use-policy).
|
||||
|
||||
**Prohibited Uses**
|
||||
|
||||
We want everyone to use Llama 4 safely and responsibly. You agree you will not use, or allow others to use, Llama 4 to:
|
||||
|
||||
1. Violate the law or others’ rights, including to:
|
||||
|
||||
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
|
||||
|
||||
1. Violence or terrorism
|
||||
|
||||
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
|
||||
|
||||
3. Human trafficking, exploitation, and sexual violence
|
||||
|
||||
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
|
||||
|
||||
5. Sexual solicitation
|
||||
|
||||
6. Any other criminal activity
|
||||
|
||||
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
|
||||
|
||||
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
|
||||
|
||||
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
|
||||
|
||||
5. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
|
||||
|
||||
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
|
||||
|
||||
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
|
||||
|
||||
8. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
|
||||
|
||||
3. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 4 related to the following:
|
||||
|
||||
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
|
||||
|
||||
2. Guns and illegal weapons (including weapon development)
|
||||
|
||||
3. Illegal drugs and regulated/controlled substances
|
||||
|
||||
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
|
||||
|
||||
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
|
||||
|
||||
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
|
||||
|
||||
4. Intentionally deceive or mislead others, including use of Llama 4 related to the following:
|
||||
|
||||
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
|
||||
|
||||
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
|
||||
|
||||
3. Generating, promoting, or further distributing spam
|
||||
|
||||
4. Impersonating another individual without consent, authorization, or legal right
|
||||
|
||||
5. Representing that the use of Llama 4 or outputs are human generated
|
||||
|
||||
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
|
||||
|
||||
5. Fail to appropriately disclose to end users any known dangers of your AI system
|
||||
|
||||
6. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 4
|
||||
|
||||
With respect to any multimodal models included in Llama 4, the rights granted under Section 1(a) of the Llama 4 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
|
||||
|
||||
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
|
||||
|
||||
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)
|
||||
* Reporting risky content generated by the model: [https://developers.facebook.com/llama_output_feedback](https://developers.facebook.com/llama_output_feedback)
|
||||
* Reporting bugs and security concerns: [https://facebook.com/whitehat/info](https://facebook.com/whitehat/info)
|
||||
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 4: LlamaUseReport@meta.com
|
||||
99
chat_template.jinja
Normal file
99
chat_template.jinja
Normal file
@@ -0,0 +1,99 @@
|
||||
{{- bos_token }}
|
||||
{%- if messages | length % 2 == 0 -%}
|
||||
{%- set role = 'Agent' -%}
|
||||
{%- else -%}
|
||||
{%- set role = 'User' -%}
|
||||
{%- endif -%}
|
||||
|
||||
{%- if categories is not defined -%}
|
||||
{%- set ns = namespace(contains_image=false) -%}
|
||||
|
||||
{%- for message in messages -%}
|
||||
{%- for content in message['content'] | selectattr('type', 'equalto', 'image') -%}
|
||||
{%- set ns.contains_image = true -%}
|
||||
{%- endfor -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{%- if ns.contains_image -%}
|
||||
{%- set categories = {
|
||||
"S1": "Violent Crimes.",
|
||||
"S2": "Non-Violent Crimes.",
|
||||
"S3": "Sex Crimes.",
|
||||
"S4": "Child Exploitation.",
|
||||
"S5": "Defamation.",
|
||||
"S6": "Specialized Advice.",
|
||||
"S7": "Privacy.",
|
||||
"S8": "Intellectual Property.",
|
||||
"S9": "Indiscriminate Weapons.",
|
||||
"S10": "Hate.",
|
||||
"S11": "Self-Harm.",
|
||||
"S12": "Sexual Content.",
|
||||
"S13": "Elections.",
|
||||
} -%}
|
||||
{%- else -%}
|
||||
{%- set categories = {
|
||||
"S1": "Violent Crimes.",
|
||||
"S2": "Non-Violent Crimes.",
|
||||
"S3": "Sex Crimes.",
|
||||
"S4": "Child Exploitation.",
|
||||
"S5": "Defamation.",
|
||||
"S6": "Specialized Advice.",
|
||||
"S7": "Privacy.",
|
||||
"S8": "Intellectual Property.",
|
||||
"S9": "Indiscriminate Weapons.",
|
||||
"S10": "Hate.",
|
||||
"S11": "Self-Harm.",
|
||||
"S12": "Sexual Content.",
|
||||
"S13": "Elections.",
|
||||
"S14": "Code Interpreter Abuse.",
|
||||
} -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
|
||||
{{ "<|begin_of_text|><|header_start|>user<|header_end|>\n" }}
|
||||
{{ "Task: Check if there is unsafe content in '" + role + "' messages in conversations according to our safety policy with the below categories.\n" }}
|
||||
{{ "<BEGIN UNSAFE CONTENT CATEGORIES>\n" }}
|
||||
|
||||
{%- for key in categories -%}
|
||||
{%- if key not in excluded_category_keys -%}
|
||||
{{ key + ": " + categories[key] + "\n" }}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{{ "<END UNSAFE CONTENT CATEGORIES>\n" }}
|
||||
{{ "<BEGIN CONVERSATION>\n" }}
|
||||
|
||||
{%- for message in messages -%}
|
||||
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
||||
{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
|
||||
{%- endif -%}
|
||||
|
||||
{%- set content = message['content'] -%}
|
||||
|
||||
{%- if message['role'] == 'user' -%}
|
||||
{%- set role = 'User' -%}
|
||||
{%- elif message['role'] == 'assistant' -%}
|
||||
{%- set role = 'Agent' -%}
|
||||
{%- endif -%}
|
||||
|
||||
{#— #1 Accumulate all images for this message —#}
|
||||
{%- set ns = namespace(img_tokens='') -%}
|
||||
{%- for img in message.content | selectattr('type', 'equalto', 'image') -%}
|
||||
{%- set ns.img_tokens = ns.img_tokens + '<|image|>' -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{#— #2 Then emit all text —#}
|
||||
{%- for txt in message.content | selectattr('type','equalto','text') -%}
|
||||
{{ role + ': ' }}{{ ns.img_tokens }}{{ txt.text | trim }}\n\n
|
||||
|
||||
{#— clear the buffer so only first text prints images —#}
|
||||
{%- if loop.first -%}
|
||||
{%- set ns.img_tokens = '' -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- endfor -%}
|
||||
|
||||
{{ "<END CONVERSATION>\n" }}
|
||||
{{ "Provide your safety assessment for ONLY THE LAST " + role + " message in the above conversation:" }}
|
||||
{{ " - First line must read 'safe' or 'unsafe'." }}
|
||||
{{ " - If unsafe, a second line must include a comma-separated list of violated categories. <|eot|><|header_start|>assistant<|header_end|>" }}
|
||||
135
config.json
Normal file
135
config.json
Normal file
@@ -0,0 +1,135 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Llama4ForConditionalGeneration"
|
||||
],
|
||||
"boi_token_index": 200080,
|
||||
"eoi_token_index": 200081,
|
||||
"image_token_index": 200092,
|
||||
"model_type": "llama4",
|
||||
"text_config": {
|
||||
"_attn_implementation_autoset": true,
|
||||
"attention_bias": false,
|
||||
"attention_chunk_size": null,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_scale": 0.1,
|
||||
"attn_temperature_tuning": true,
|
||||
"bos_token_id": 200000,
|
||||
"cache_implementation": "static",
|
||||
"eos_token_id": [
|
||||
200001,
|
||||
200007,
|
||||
200008
|
||||
],
|
||||
"floor_scale": 8192,
|
||||
"for_llm_compressor": false,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"interleave_moe_layer_step": 0,
|
||||
"intermediate_size": 8192,
|
||||
"intermediate_size_mlp": 8192,
|
||||
"max_position_embeddings": 10485760,
|
||||
"model_type": "llama4_text",
|
||||
"moe_layers": [],
|
||||
"no_rope_layers": [
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1,
|
||||
1
|
||||
],
|
||||
"num_attention_heads": 40,
|
||||
"num_experts_per_tok": 1,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"num_local_experts": 0,
|
||||
"output_router_logits": false,
|
||||
"pad_token_id": 200018,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 16,
|
||||
"high_freq_factor": 1,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"router_jitter_noise": 0.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_cache": true,
|
||||
"use_qk_norm": true,
|
||||
"vocab_size": 202048
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.0.dev0",
|
||||
"vision_config": {
|
||||
"_attn_implementation_autoset": true,
|
||||
"attention_dropout": 0.0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 1408,
|
||||
"image_size": 336,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"model_type": "llama4_vision_model",
|
||||
"multi_modal_projector_bias": false,
|
||||
"norm_eps": 1e-05,
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 34,
|
||||
"patch_size": 14,
|
||||
"pixel_shuffle_ratio": 0.5,
|
||||
"projector_dropout": 0.0,
|
||||
"projector_input_dim": 4096,
|
||||
"projector_output_dim": 4096,
|
||||
"rope_theta": 10000,
|
||||
"vision_feature_layer": -1,
|
||||
"vision_feature_select_strategy": "default",
|
||||
"vision_output_dim": 4096
|
||||
}
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 200000,
|
||||
"cache_implementation": "static",
|
||||
"eos_token_id": [
|
||||
200001,
|
||||
200007,
|
||||
200008
|
||||
],
|
||||
"pad_token_id": 200018,
|
||||
"transformers_version": "4.52.0.dev0"
|
||||
}
|
||||
BIN
llama_guard_4_12b_after_pruning.png
Normal file
BIN
llama_guard_4_12b_after_pruning.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
BIN
llama_guard_4_12b_before_pruning.png
Normal file
BIN
llama_guard_4_12b_before_pruning.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 105 KiB |
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b3e93a5c09f732537068482a5f00c29a675092f0ae456ebd60043af59c21299
|
||||
size 4997861792
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:08150644f6be3ae2474a8a9f3290edbc62ac876522217c6bf70ce304ed1351e2
|
||||
size 4981018296
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d30c028733fc776ac18a369d565bb395fa4473aa2317cbedeef1cd216c6b327
|
||||
size 4991503856
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ecd9fed60f059359941913c3ade611e8c67a63ba453efbc071de8af007c586e7
|
||||
size 4991503856
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57aa2d6a20feb15010f74599e4a4f9f4985cb1b87a975dc6ffc1d34780de7599
|
||||
size 4040434224
|
||||
996
model.safetensors.index.json
Normal file
996
model.safetensors.index.json
Normal file
@@ -0,0 +1,996 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24002194432
|
||||
},
|
||||
"weight_map": {
|
||||
"language_model.lm_head.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.16.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.feed_forward.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.29.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.40.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.feed_forward.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.42.feed_forward.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.feed_forward.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"language_model.model.layers.43.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.feed_forward.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.feed_forward.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.feed_forward.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.feed_forward.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"language_model.model.norm.weight": "model-00005-of-00005.safetensors",
|
||||
"multi_modal_projector.linear_1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.class_embedding": "model-00001-of-00005.safetensors",
|
||||
"vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.32.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.33.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.o_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||
"vision_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.patch_embedding.linear.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.positional_embedding_vlm": "model-00001-of-00005.safetensors",
|
||||
"vision_model.vision_adapter.mlp.fc1.weight": "model-00001-of-00005.safetensors",
|
||||
"vision_model.vision_adapter.mlp.fc2.weight": "model-00001-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
33
preprocessor_config.json
Normal file
33
preprocessor_config.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Llama4ImageProcessorFast",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_patches": 16,
|
||||
"processor_class": "Llama4Processor",
|
||||
"resample": 2,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"resize_to_max_canvas": false,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"height": 336,
|
||||
"width": 336
|
||||
}
|
||||
}
|
||||
6
processor_config.json
Normal file
6
processor_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"fake_image_token": "<|image|>",
|
||||
"image_token": "<|image|>",
|
||||
"patch_size": 14,
|
||||
"processor_class": "Llama4Processor"
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|finetune_right_pad_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:22e009b4fcb58eddbabf347e71b9881ea1e6eb72d44e5ea9477c7587df68fd8d
|
||||
size 27948580
|
||||
9100
tokenizer_config.json
Normal file
9100
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user