Duplicate from convergence-ai/proxy-lite-3b
Browse filesCo-authored-by: Alex J. Chan <XanderJC@users.noreply.huggingface.co>
- .gitattributes +36 -0
- README.md +212 -0
- added_tokens.json +24 -0
- chat_template.json +3 -0
- config.json +51 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +831 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +211 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- agent
|
| 5 |
+
- action
|
| 6 |
+
- vlm
|
| 7 |
+
base_model: Qwen/Qwen2.5-VL-3B-Instruct
|
| 8 |
+
license: cc-by-nc-4.0
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Proxy Lite
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
<div align="center">
|
| 16 |
+
<img src="https://raw.githubusercontent.com/convergence-ai/proxy-lite/refs/heads/main/assets/proxy-lite.png" alt="Proxy Lite logo" width="600" height="auto" style="margin-bottom: 20px;" />
|
| 17 |
+
<h2>
|
| 18 |
+
A mini, open-weights, version of <a href="https://proxy.convergence.ai">Proxy</a>.
|
| 19 |
+
</h2>
|
| 20 |
+
</div>
|
| 21 |
+
|
| 22 |
+
## Model Description
|
| 23 |
+
|
| 24 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 25 |
+
|
| 26 |
+
- **Developed by:** Convergence AI
|
| 27 |
+
- **Model type:** 3B Vision-Language Model
|
| 28 |
+
- **Agent type**: Web-browsing Agent
|
| 29 |
+
- **License:** CC-BY-NC-4.0
|
| 30 |
+
- **Finetuned from model:** Qwen/Qwen2.5-VL-3B-Instruct
|
| 31 |
+
- [Running the agent](https://github.com/convergence-ai/proxy-lite)
|
| 32 |
+
|
| 33 |
+
## Running Proxy on the web
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
https://github.com/convergence-ai/proxy-lite to run Proxy lite on a browser
|
| 38 |
+
|
| 39 |
+
```
|
| 40 |
+
git clone https://github.com/convergence-ai/proxy-lite.git
|
| 41 |
+
make proxy
|
| 42 |
+
proxy "Find some markets near Kings Cross and tell me their ratings."
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
<div align="center">
|
| 46 |
+
<img src="https://raw.githubusercontent.com/convergence-ai/proxy-lite/refs/heads/main/assets/demo.gif" alt="Proxy Lite Demo" />
|
| 47 |
+
</div>
|
| 48 |
+
|
| 49 |
+
## Uses
|
| 50 |
+
|
| 51 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 52 |
+
|
| 53 |
+
Proxy Lite is designed and trained to complete automated tasks in a web browser.
|
| 54 |
+
|
| 55 |
+
Full code for running the model is available in the [github repository](https://github.com/convergence-ai/proxy-lite).
|
| 56 |
+
|
| 57 |
+
This includes a CLI tool for running the model, as well as a streamlit app.
|
| 58 |
+
|
| 59 |
+
You can use this [endpoint](https://huggingface.co/spaces/convergence-ai/demo-api) for small-scale testing.
|
| 60 |
+
|
| 61 |
+
---
|
| 62 |
+
|
| 63 |
+
#### Direct Use
|
| 64 |
+
|
| 65 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 66 |
+
|
| 67 |
+
We recommend hosting your own endpoint with vLLM, you can use the following command:
|
| 68 |
+
|
| 69 |
+
```bash
|
| 70 |
+
vllm serve convergence-ai/proxy-lite-3b \
|
| 71 |
+
--trust-remote-code \
|
| 72 |
+
--enable-auto-tool-choice \
|
| 73 |
+
--tool-call-parser hermes \
|
| 74 |
+
--port 8008 \
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
The tool arguments are **very important** for parsing the tool calls from the model appropriately.
|
| 78 |
+
|
| 79 |
+
> **Important:** Qwen-2.5-VL Support in `transformers` is not yet available in the latest release so be sure to install from source.
|
| 80 |
+
|
| 81 |
+
#### Message History
|
| 82 |
+
|
| 83 |
+
When it comes to using and prompting Proxy Lite, please refer to the [repository](https://github.com/convergence-ai/proxy-lite) for more information, but the model expects a message history of the form:
|
| 84 |
+
|
| 85 |
+
```python
|
| 86 |
+
message_history = [
|
| 87 |
+
{
|
| 88 |
+
"role": "system",
|
| 89 |
+
"content": "You are Proxy Lite...", # Full system prompt in src/proxy_lite/agents/proxy_lite_agent.py
|
| 90 |
+
}, # System prompt
|
| 91 |
+
{
|
| 92 |
+
"role": "user",
|
| 93 |
+
"content": "Find some markets near Kings Cross and tell me their ratings.",
|
| 94 |
+
}, # Set the task
|
| 95 |
+
{
|
| 96 |
+
"role": "user",
|
| 97 |
+
"content": [
|
| 98 |
+
{"type": "image_url", "image_url": {base64_encoded_screenshot} },
|
| 99 |
+
{"type": "text", "text": "URL: https://www.google.com/ \n- [0] <a>About</a> \n- [1] <a>Store</a>...."}
|
| 100 |
+
] # This is the observation from the environment
|
| 101 |
+
},
|
| 102 |
+
]
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
This would then build up the message history, alternating between the assistant (who takes the *action*) and the user (who provides the *observation*).
|
| 106 |
+
|
| 107 |
+
> **Context-Window Management:** When making calls to the model, all the observations other than the current one are discarded in order to reduce the large number of image tokens required. Since the model responses include reflection on the observations and are all included in the message history, the model is still aware of the entire history when planning new actions.
|
| 108 |
+
|
| 109 |
+
#### Tools
|
| 110 |
+
|
| 111 |
+
You should also pass the `Tools` that the model has access to, these will define the action space available to the model. You can do this with `transformers`:
|
| 112 |
+
|
| 113 |
+
```python
|
| 114 |
+
from qwen_vl_utils import process_vision_info
|
| 115 |
+
from transformers import AutoProcessor
|
| 116 |
+
|
| 117 |
+
from proxy_lite.tools import ReturnValueTool, BrowserTool
|
| 118 |
+
from proxy_lite.serializer import OpenAICompatableSerializer
|
| 119 |
+
|
| 120 |
+
processor = AutoProcessor.from_pretrained("convergence-ai/proxy-lite-3b")
|
| 121 |
+
tools = OpenAICompatableSerializer().serialize_tools([ReturnValueTool(), BrowserTool(session=None)])
|
| 122 |
+
|
| 123 |
+
templated_messages = processor.apply_chat_template(
|
| 124 |
+
message_history, tokenize=False, add_generation_prompt=True, tools=tools
|
| 125 |
+
)
|
| 126 |
+
|
| 127 |
+
image_inputs, video_inputs = process_vision_info(message_history)
|
| 128 |
+
|
| 129 |
+
batch = processor(
|
| 130 |
+
text=[templated_messages],
|
| 131 |
+
images=image_inputs,
|
| 132 |
+
videos=video_inputs,
|
| 133 |
+
padding=True,
|
| 134 |
+
return_tensors="pt",
|
| 135 |
+
)
|
| 136 |
+
```
|
| 137 |
+
|
| 138 |
+
Or you can send to the endpoint directly, which will handle the formatting:
|
| 139 |
+
|
| 140 |
+
```python
|
| 141 |
+
from openai import OpenAI
|
| 142 |
+
|
| 143 |
+
client = OpenAI(base_url="http://convergence-ai-demo-api.hf.space/v1")
|
| 144 |
+
|
| 145 |
+
response = client.chat.completions.create(
|
| 146 |
+
model="convergence-ai/proxy-lite-3b",
|
| 147 |
+
messages=message_history,
|
| 148 |
+
tools=tools,
|
| 149 |
+
tool_choice="auto",
|
| 150 |
+
)
|
| 151 |
+
```
|
| 152 |
+
|
| 153 |
+
---
|
| 154 |
+
|
| 155 |
+
## Evaluation
|
| 156 |
+
|
| 157 |
+
Proxy Lite scored 72.4% on the [WebVoyager](https://huggingface.co/datasets/convergence-ai/WebVoyager2025Valid) benchmark, placing it 1st out of all available open-weights models.
|
| 158 |
+
|
| 159 |
+
A breakdown of the results by website is shown below:
|
| 160 |
+
|
| 161 |
+
| web_name | Success Rate (%) | Finish Rate (%) | Avg. Steps |
|
| 162 |
+
|---------------------|-----------------|-----------------|------------|
|
| 163 |
+
| Allrecipes | 87.8 | 95.1 | 10.3 |
|
| 164 |
+
| Amazon | 70.0 | 90.0 | 7.1 |
|
| 165 |
+
| Apple | 82.1 | 89.7 | 10.7 |
|
| 166 |
+
| ArXiv | 60.5 | 79.1 | 16.0 |
|
| 167 |
+
| BBC News | 69.4 | 77.8 | 15.9 |
|
| 168 |
+
| Booking | 70.0 | 85.0 | 24.8 |
|
| 169 |
+
| Cambridge Dict. | 86.0 | 97.7 | 5.7 |
|
| 170 |
+
| Coursera | 82.5 | 97.5 | 4.7 |
|
| 171 |
+
| ESPN | 53.8 | 87.2 | 14.9 |
|
| 172 |
+
| GitHub | 85.0 | 92.5 | 10.0 |
|
| 173 |
+
| Google Flights | 38.5 | 51.3 | 34.8 |
|
| 174 |
+
| Google Map | 78.9 | 94.7 | 9.6 |
|
| 175 |
+
| Google Search | 71.4 | 92.9 | 6.0 |
|
| 176 |
+
| Huggingface | 68.6 | 74.3 | 18.4 |
|
| 177 |
+
| Wolfram Alpha | 78.3 | 93.5 | 6.1 |
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
---
|
| 181 |
+
|
| 182 |
+
## Out-of-Scope Use
|
| 183 |
+
|
| 184 |
+
Proxy Lite is specifically designed to automate routine tasks within a web browser environment. However, it should **not be used** for:
|
| 185 |
+
|
| 186 |
+
- **High-Stakes or Safety-Critical Applications:**
|
| 187 |
+
_Avoid using Proxy Lite for tasks such as financial transactions, healthcare operations, legal decision-making, or emergency responses, where any error could lead to serious harm or significant financial loss._
|
| 188 |
+
|
| 189 |
+
- **Unauthorized or Invasive Data Extraction:**
|
| 190 |
+
_Automated scraping or extraction of data from websites should only be performed with explicit permission. Proxy Lite should not be used to bypass websites' terms of service, copyright restrictions, or privacy policies._
|
| 191 |
+
|
| 192 |
+
- **Interactions with Malicious or Unverified Websites:**
|
| 193 |
+
_Using the model to navigate or interact with suspicious or untrusted websites may expose the system to security threats such as malware, phishing attacks, or other forms of cyber exploitation._
|
| 194 |
+
|
| 195 |
+
- **Compliance-Regulated or Legally Sensitive Actions:**
|
| 196 |
+
_Tasks that require adherence to strict legal or regulatory standards (e.g., processing personal data or sensitive information) should employ additional safeguards beyond what the model provides._
|
| 197 |
+
|
| 198 |
+
---
|
| 199 |
+
|
| 200 |
+
## Citation
|
| 201 |
+
|
| 202 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 203 |
+
|
| 204 |
+
**BibTeX:**
|
| 205 |
+
|
| 206 |
+
```bibtex
|
| 207 |
+
@article{proxy-lite,
|
| 208 |
+
title={Proxy Lite - A Mini, Open-weights, Autonomous Assistant},
|
| 209 |
+
author={Convergence AI},
|
| 210 |
+
year={2025}
|
| 211 |
+
}
|
| 212 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{{- '<|im_start|>' + messages[0].role + '\n' }}{%- if messages[0]['content'] is string %}{{ messages[0]['content'] }}{%- else %}{%- for content in messages[0]['content'] %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{%- if messages[0].tool_calls %}{%- for tool_call in messages[0].tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments | tojson }}} </tool_call>{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- if tools %}{{- '<|im_start|>system\n' }}{{- \"\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\" }}{%- for tool in tools %}{{- \"\n\" }}{{- tool | tojson }}{%- endfor %}{{- \"\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n\" }}<tool_call>{\"name\": <function-name>, \"arguments\": <args-json-object>}</tool_call>{{- '<|im_end|>\n' }}{%- endif %}{%- for message in messages[1:] %}{%- if (message.role == \"user\") or (message.role == \"system\") or (message.role == \"assistant\" and not message.tool_calls) %}{{- '<|im_start|>' + message.role + '\n' }}{%- if message.content is string %}{{ message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- elif message.role == \"assistant\" %}{{- '<|im_start|>' + message.role }}{%- if message.content %}{% if message.content is string %}{{ '\n' + message.content }}{% else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{% endif %}{%- endif %}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments | tojson }}} </tool_call>{%- endfor %}{{- '<|im_end|>\n' }}{%- elif message.role == \"tool\" %}{%- if (loop.index0 == 0) or (messages[loop.index0].role != \"tool\") %}{{- '<|im_start|>user' }}{%- endif %}{{- '\n<tool_response>\n' }}{%- if message.content is string %}{{ message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '\n</tool_response>' }}{%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}{{- '<|im_end|>\n' }}{%- endif %}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "convergence-ai/subset-distill-tools-3b-17-02-2025",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 70,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": {
|
| 22 |
+
"mrope_section": [
|
| 23 |
+
16,
|
| 24 |
+
24,
|
| 25 |
+
24
|
| 26 |
+
],
|
| 27 |
+
"rope_type": "default",
|
| 28 |
+
"type": "default"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 1000000.0,
|
| 31 |
+
"sliding_window": 32768,
|
| 32 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.49.0.dev0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"video_token_id": 151656,
|
| 38 |
+
"vision_config": {
|
| 39 |
+
"hidden_size": 1280,
|
| 40 |
+
"in_chans": 3,
|
| 41 |
+
"model_type": "qwen2_5_vl",
|
| 42 |
+
"out_hidden_size": 2048,
|
| 43 |
+
"spatial_patch_size": 14,
|
| 44 |
+
"tokens_per_second": 2,
|
| 45 |
+
"torch_dtype": "bfloat16"
|
| 46 |
+
},
|
| 47 |
+
"vision_end_token_id": 151653,
|
| 48 |
+
"vision_start_token_id": 151652,
|
| 49 |
+
"vision_token_id": 151654,
|
| 50 |
+
"vocab_size": 151936
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.49.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75ea96512ea39fcf7b30684b2d0cea6b96e01edcacdfc482fdd3c226177cecd7
|
| 3 |
+
size 4997750760
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:875b99829f1d38caeda774a050dfce6a4546340ffd6db0c0712cd9239ace4b0d
|
| 3 |
+
size 2511587184
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,831 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 7509245952
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 358 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 359 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 440 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 739 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 745 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 746 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 749 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 750 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 752 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 753 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 755 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 756 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 757 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 758 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 759 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 761 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 763 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 764 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 767 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 768 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 771 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 772 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 775 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 776 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 777 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 778 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 779 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 781 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 782 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 783 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 784 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 785 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 789 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 790 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 793 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 794 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 797 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 798 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 799 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 801 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 802 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 803 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 804 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 805 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 807 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 808 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 809 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 810 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 811 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 813 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 815 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 816 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 817 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 818 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 819 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 820 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 821 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 822 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 823 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 824 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 825 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 826 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 827 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 828 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 829 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
|
| 830 |
+
}
|
| 831 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{{- '<|im_start|>' + messages[0].role + '\n' }}{%- if messages[0]['content'] is string %}{{ messages[0]['content'] }}{%- else %}{%- for content in messages[0]['content'] %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{%- if messages[0].tool_calls %}{%- for tool_call in messages[0].tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments | tojson }}} </tool_call>{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- if tools %}{{- '<|im_start|>system\n' }}{{- \"\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\" }}{%- for tool in tools %}{{- \"\n\" }}{{- tool | tojson }}{%- endfor %}{{- \"\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n\" }}<tool_call>{\"name\": <function-name>, \"arguments\": <args-json-object>}</tool_call>{{- '<|im_end|>\n' }}{%- endif %}{%- for message in messages[1:] %}{%- if (message.role == \"user\") or (message.role == \"system\") or (message.role == \"assistant\" and not message.tool_calls) %}{{- '<|im_start|>' + message.role + '\n' }}{%- if message.content is string %}{{ message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '<|im_end|>\n' }}{%- elif message.role == \"assistant\" %}{{- '<|im_start|>' + message.role }}{%- if message.content %}{% if message.content is string %}{{ '\n' + message.content }}{% else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{% endif %}{%- endif %}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}<tool_call>{\"name\": \"{{ tool_call.name }}\", \"arguments\": {{ tool_call.arguments | tojson }}} </tool_call>{%- endfor %}{{- '<|im_end|>\n' }}{%- elif message.role == \"tool\" %}{%- if (loop.index0 == 0) or (messages[loop.index0].role != \"tool\") %}{{- '<|im_start|>user' }}{%- endif %}{{- '\n<tool_response>\n' }}{%- if message.content is string %}{{ message.content }}{%- else %}{%- for content in message.content %}{%- if content.type == 'image' or ('image' in content) or ('image_url' in content) %}{% set image_count.value = image_count.value + 1 %}{%- if add_vision_id %}Picture {{ image_count.value }}:{%- endif %}<|vision_start|><|image_pad|><|vision_end|>{%- elif content.type == 'video' or ('video' in content) %}{% set video_count.value = video_count.value + 1 %}{%- if add_vision_id %}Video {{ video_count.value }}:{%- endif %}<|vision_start|><|video_pad|><|vision_end|>{%- elif 'text' in content %}{{ content.text }}{%- endif %}{%- endfor %}{%- endif %}{{- '\n</tool_response>' }}{%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}{{- '<|im_end|>\n' }}{%- endif %}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant\n' }}{%- endif %}",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"do_image_splitting": false,
|
| 201 |
+
"eos_token": "<|im_end|>",
|
| 202 |
+
"errors": "replace",
|
| 203 |
+
"extra_special_tokens": {},
|
| 204 |
+
"model_max_length": 131072,
|
| 205 |
+
"pad_token": "<|endoftext|>",
|
| 206 |
+
"padding_side": "left",
|
| 207 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 208 |
+
"split_special_tokens": false,
|
| 209 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 210 |
+
"unk_token": null
|
| 211 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|