Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +8 -236
- config.json +20 -964
- model-00001-of-00046.safetensors +2 -2
- model-00002-of-00046.safetensors +2 -2
- model-00003-of-00046.safetensors +2 -2
- model-00004-of-00046.safetensors +2 -2
- model-00005-of-00046.safetensors +2 -2
- model-00006-of-00046.safetensors +2 -2
- model-00007-of-00046.safetensors +2 -2
- model-00008-of-00046.safetensors +2 -2
- model-00009-of-00046.safetensors +2 -2
- model-00010-of-00046.safetensors +2 -2
- model-00011-of-00046.safetensors +2 -2
- model-00012-of-00046.safetensors +2 -2
- model-00013-of-00046.safetensors +2 -2
- model-00014-of-00046.safetensors +2 -2
- model-00015-of-00046.safetensors +2 -2
- model-00016-of-00046.safetensors +2 -2
- model-00017-of-00046.safetensors +2 -2
- model-00018-of-00046.safetensors +2 -2
- model-00019-of-00046.safetensors +2 -2
- model-00020-of-00046.safetensors +2 -2
- model-00021-of-00046.safetensors +2 -2
- model-00022-of-00046.safetensors +2 -2
- model-00023-of-00046.safetensors +2 -2
- model-00024-of-00046.safetensors +2 -2
- model-00025-of-00046.safetensors +2 -2
- model-00026-of-00046.safetensors +2 -2
- model-00027-of-00046.safetensors +2 -2
- model-00028-of-00046.safetensors +2 -2
- model-00029-of-00046.safetensors +2 -2
- model-00030-of-00046.safetensors +2 -2
- model-00031-of-00046.safetensors +2 -2
- model-00032-of-00046.safetensors +2 -2
- model-00033-of-00046.safetensors +2 -2
- model-00034-of-00046.safetensors +2 -2
- model-00035-of-00046.safetensors +2 -2
- model-00036-of-00046.safetensors +2 -2
- model-00037-of-00046.safetensors +2 -2
- model-00038-of-00046.safetensors +2 -2
- model-00039-of-00046.safetensors +2 -2
- model-00040-of-00046.safetensors +2 -2
- model-00041-of-00046.safetensors +2 -2
- model-00042-of-00046.safetensors +2 -2
- model-00043-of-00046.safetensors +2 -2
- model-00044-of-00046.safetensors +2 -2
- model-00045-of-00046.safetensors +2 -2
- model-00046-of-00046.safetensors +2 -2
- model.safetensors.index.json +335 -3
- preprocessor_config.json +21 -0
README.md
CHANGED
|
@@ -1,249 +1,21 @@
|
|
| 1 |
---
|
| 2 |
-
library_name:
|
| 3 |
license: apache-2.0
|
| 4 |
license_link: https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE
|
| 5 |
-
|
| 6 |
-
pipeline_tag: text-generation
|
| 7 |
tags:
|
| 8 |
- mlx
|
| 9 |
-
- 4bit
|
| 10 |
-
- quantized
|
| 11 |
-
- qwen3_5_moe
|
| 12 |
-
- moe
|
| 13 |
-
- mixture-of-experts
|
| 14 |
-
- text-generation
|
| 15 |
-
- conversational
|
| 16 |
-
- apple-silicon
|
| 17 |
-
language:
|
| 18 |
-
- multilingual
|
| 19 |
---
|
| 20 |
|
| 21 |
-
# Qwen3.5-397B-A17B-4bit
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
Portions of this card were copied or adapted from the original model card, authored by the Qwen team.
|
| 26 |
-
|
| 27 |
-
## Model Overview
|
| 28 |
-
|
| 29 |
-
Qwen3.5-397B-A17B is Alibaba's latest flagship language model, featuring a hybrid architecture that combines Gated DeltaNet (linear attention) with sparse Mixture-of-Experts for high-throughput inference. Despite having 397B total parameters, only ~17B are activated per token, making it remarkably efficient for its capability level.
|
| 30 |
-
|
| 31 |
-
This conversion provides a **text-only** 4-bit quantized version optimized for local inference on Apple Silicon Macs via the MLX framework. The vision encoder from the original multimodal model is not included — for image/video understanding, refer to the original [Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B).
|
| 32 |
-
|
| 33 |
-
### Key Capabilities
|
| 34 |
-
|
| 35 |
-
- **201 languages and dialects** with deep cultural and regional understanding
|
| 36 |
-
- **262K native context** (extensible to 1M+ with YaRN)
|
| 37 |
-
- **Thinking mode** with chain-of-thought reasoning (`<think>...</think>`)
|
| 38 |
-
- **Tool use and agentic workflows** (MCP, function calling)
|
| 39 |
-
- **Competitive benchmarks**: MMLU-Pro 87.8, SuperGPQA 70.4, C-Eval 93.0
|
| 40 |
-
|
| 41 |
-
## Architecture
|
| 42 |
-
|
| 43 |
-
| Parameter | Value |
|
| 44 |
-
|---|---|
|
| 45 |
-
| Total Parameters | 397B |
|
| 46 |
-
| Active Parameters | ~17B |
|
| 47 |
-
| Hidden Size | 4,096 |
|
| 48 |
-
| Layers | 60 |
|
| 49 |
-
| Layer Layout | 15 × (3 × Gated DeltaNet + 1 × Full Attention), all with MoE FFN |
|
| 50 |
-
| Total Experts | 512 |
|
| 51 |
-
| Active Experts per Token | 10 routed + 1 shared |
|
| 52 |
-
| Expert Intermediate Size | 1,024 |
|
| 53 |
-
| Full Attention Heads | 32 Q / 2 KV (GQA), head dim 256 |
|
| 54 |
-
| Linear Attention Heads | 16 QK / 64 V, head dim 128 |
|
| 55 |
-
| Context Length | 262,144 tokens |
|
| 56 |
-
| Vocab Size | 248,320 |
|
| 57 |
-
|
| 58 |
-
## Quantization Details
|
| 59 |
-
|
| 60 |
-
| Parameter | Value |
|
| 61 |
-
|---|---|
|
| 62 |
-
| Method | Affine quantization |
|
| 63 |
-
| Bits | 4-bit (weights) |
|
| 64 |
-
| Group Size | 64 |
|
| 65 |
-
| MoE Router Gates | 8-bit (preserved at higher precision) |
|
| 66 |
-
| Model Size on Disk | ~223 GB |
|
| 67 |
-
|
| 68 |
-
The MoE router gates (`mlp.gate` and `mlp.shared_expert_gate` for all 60 layers) are kept at 8-bit precision to preserve routing accuracy, which is critical for Mixture-of-Experts models.
|
| 69 |
-
|
| 70 |
-
## Requirements
|
| 71 |
-
|
| 72 |
-
- Apple Silicon Mac with **at least 256 GB unified memory** (e.g., Mac Studio M3 Ultra 256GB+)
|
| 73 |
-
- Python 3.10+
|
| 74 |
-
- [`mlx-lm`](https://github.com/ml-explore/mlx-lm) from the `main` branch
|
| 75 |
-
|
| 76 |
-
## Installation
|
| 77 |
|
| 78 |
```bash
|
| 79 |
-
pip install
|
| 80 |
```
|
| 81 |
|
| 82 |
-
## Usage
|
| 83 |
-
|
| 84 |
-
### Quick Start — Python API
|
| 85 |
-
|
| 86 |
-
```python
|
| 87 |
-
from mlx_lm import load, generate
|
| 88 |
-
|
| 89 |
-
model, tokenizer = load("mlx-community/Qwen3.5-397B-A17B-4bit")
|
| 90 |
-
|
| 91 |
-
messages = [{"role": "user", "content": "Explain the Riemann hypothesis in simple terms."}]
|
| 92 |
-
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
|
| 93 |
-
|
| 94 |
-
response = generate(
|
| 95 |
-
model,
|
| 96 |
-
tokenizer,
|
| 97 |
-
prompt=prompt,
|
| 98 |
-
max_tokens=4096,
|
| 99 |
-
verbose=True,
|
| 100 |
-
temp=0.6,
|
| 101 |
-
top_p=0.95,
|
| 102 |
-
)
|
| 103 |
-
```
|
| 104 |
-
|
| 105 |
-
### Thinking Mode (Default)
|
| 106 |
-
|
| 107 |
-
The model defaults to thinking mode, producing chain-of-thought reasoning inside `<think>...</think>` tags before the final answer:
|
| 108 |
-
|
| 109 |
-
```python
|
| 110 |
-
from mlx_lm import load, generate
|
| 111 |
-
|
| 112 |
-
model, tokenizer = load("mlx-community/Qwen3.5-397B-A17B-4bit")
|
| 113 |
-
|
| 114 |
-
messages = [
|
| 115 |
-
{"role": "user", "content": "How many r's are in the word 'strawberry'?"}
|
| 116 |
-
]
|
| 117 |
-
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
|
| 118 |
-
|
| 119 |
-
response = generate(
|
| 120 |
-
model,
|
| 121 |
-
tokenizer,
|
| 122 |
-
prompt=prompt,
|
| 123 |
-
max_tokens=8192,
|
| 124 |
-
verbose=True,
|
| 125 |
-
temp=0.6,
|
| 126 |
-
top_p=0.95,
|
| 127 |
-
)
|
| 128 |
-
```
|
| 129 |
-
|
| 130 |
-
### Non-Thinking Mode
|
| 131 |
-
|
| 132 |
-
For faster, more direct responses without chain-of-thought reasoning:
|
| 133 |
-
|
| 134 |
-
```python
|
| 135 |
-
from mlx_lm import load, generate
|
| 136 |
-
|
| 137 |
-
model, tokenizer = load("mlx-community/Qwen3.5-397B-A17B-4bit")
|
| 138 |
-
|
| 139 |
-
messages = [
|
| 140 |
-
{"role": "user", "content": "Write a haiku about machine learning."}
|
| 141 |
-
]
|
| 142 |
-
prompt = tokenizer.apply_chat_template(
|
| 143 |
-
messages,
|
| 144 |
-
add_generation_prompt=True,
|
| 145 |
-
enable_thinking=False,
|
| 146 |
-
)
|
| 147 |
-
|
| 148 |
-
response = generate(
|
| 149 |
-
model,
|
| 150 |
-
tokenizer,
|
| 151 |
-
prompt=prompt,
|
| 152 |
-
max_tokens=2048,
|
| 153 |
-
verbose=True,
|
| 154 |
-
temp=0.7,
|
| 155 |
-
top_p=0.8,
|
| 156 |
-
)
|
| 157 |
-
```
|
| 158 |
-
|
| 159 |
-
### Command Line
|
| 160 |
-
|
| 161 |
-
```bash
|
| 162 |
-
# Thinking mode (default)
|
| 163 |
-
mlx_lm.generate \
|
| 164 |
-
--model mlx-community/Qwen3.5-397B-A17B-4bit \
|
| 165 |
-
--prompt "What are the key differences between TCP and UDP?" \
|
| 166 |
-
--max-tokens 4096 \
|
| 167 |
-
--temp 0.6 \
|
| 168 |
-
--top-p 0.95
|
| 169 |
-
|
| 170 |
-
# Start a local chat server (OpenAI-compatible)
|
| 171 |
-
mlx_lm.server --model mlx-community/Qwen3.5-397B-A17B-4bit
|
| 172 |
-
```
|
| 173 |
-
|
| 174 |
-
### Local OpenAI-Compatible Server
|
| 175 |
-
|
| 176 |
-
Start the server:
|
| 177 |
-
|
| 178 |
-
```bash
|
| 179 |
-
mlx_lm.server --model mlx-community/Qwen3.5-397B-A17B-4bit --port 8080
|
| 180 |
-
```
|
| 181 |
-
|
| 182 |
-
Then query it with any OpenAI-compatible client:
|
| 183 |
-
|
| 184 |
-
```python
|
| 185 |
-
from openai import OpenAI
|
| 186 |
-
|
| 187 |
-
client = OpenAI(base_url="http://localhost:8080/v1", api_key="unused")
|
| 188 |
-
|
| 189 |
-
response = client.chat.completions.create(
|
| 190 |
-
model="mlx-community/Qwen3.5-397B-A17B-4bit",
|
| 191 |
-
messages=[
|
| 192 |
-
{"role": "system", "content": "You are a helpful assistant."},
|
| 193 |
-
{"role": "user", "content": "Write a Python function to find all prime numbers up to n using the Sieve of Eratosthenes."},
|
| 194 |
-
],
|
| 195 |
-
max_tokens=4096,
|
| 196 |
-
temperature=0.6,
|
| 197 |
-
top_p=0.95,
|
| 198 |
-
)
|
| 199 |
-
print(response.choices[0].message.content)
|
| 200 |
-
```
|
| 201 |
-
|
| 202 |
-
Or with `curl`:
|
| 203 |
-
|
| 204 |
```bash
|
| 205 |
-
|
| 206 |
-
-H "Content-Type: application/json" \
|
| 207 |
-
-d '{
|
| 208 |
-
"model": "mlx-community/Qwen3.5-397B-A17B-4bit",
|
| 209 |
-
"messages": [{"role": "user", "content": "Hello!"}],
|
| 210 |
-
"max_tokens": 512,
|
| 211 |
-
"temperature": 0.6
|
| 212 |
-
}'
|
| 213 |
-
```
|
| 214 |
-
|
| 215 |
-
## Recommended Generation Parameters
|
| 216 |
-
|
| 217 |
-
| Parameter | Thinking Mode | Non-Thinking Mode |
|
| 218 |
-
|---|---|---|
|
| 219 |
-
| `temperature` | 0.6 | 0.7 |
|
| 220 |
-
| `top_p` | 0.95 | 0.8 |
|
| 221 |
-
| `top_k` | 20 | 20 |
|
| 222 |
-
| `presence_penalty` | 0.0 | 1.5 |
|
| 223 |
-
| `repetition_penalty` | 1.0 | 1.0 |
|
| 224 |
-
| `max_tokens` (general) | 32,768 | 32,768 |
|
| 225 |
-
| `max_tokens` (math/code) | 81,920 | — |
|
| 226 |
-
|
| 227 |
-
## Tips
|
| 228 |
-
|
| 229 |
-
- **Thinking mode** is best for complex reasoning, math, and coding tasks. The model will produce internal reasoning before answering.
|
| 230 |
-
- **Non-thinking mode** is better for straightforward Q&A, creative writing, and conversational use where latency matters.
|
| 231 |
-
- For **math problems**, append: *"Please reason step by step, and put your final answer within \boxed{}."*
|
| 232 |
-
- For **multi-turn conversations**, the default chat template automatically strips thinking content from prior turns.
|
| 233 |
-
- If running into **memory pressure**, consider closing other applications to free unified memory.
|
| 234 |
-
|
| 235 |
-
## Original Model
|
| 236 |
-
|
| 237 |
-
This is a quantized version of [Qwen/Qwen3.5-397B-A17B](https://huggingface.co/Qwen/Qwen3.5-397B-A17B). Refer to the original model card for full benchmark results, training details, and the technical report.
|
| 238 |
-
|
| 239 |
-
## Citation
|
| 240 |
-
|
| 241 |
-
```bibtex
|
| 242 |
-
@misc{qwen3.5,
|
| 243 |
-
title = {{Qwen3.5}: Towards Native Multimodal Agents},
|
| 244 |
-
author = {{Qwen Team}},
|
| 245 |
-
month = {February},
|
| 246 |
-
year = {2026},
|
| 247 |
-
url = {https://qwen.ai/blog?id=qwen3.5}
|
| 248 |
-
}
|
| 249 |
```
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
license_link: https://huggingface.co/Qwen/Qwen3.5-397B-A17B/blob/main/LICENSE
|
| 5 |
+
pipeline_tag: image-text-to-text
|
|
|
|
| 6 |
tags:
|
| 7 |
- mlx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# mlx-community/Qwen3.5-397B-A17B-4bit
|
| 11 |
+
This model was converted to MLX format from [`Qwen/Qwen3.5-397B-A17B`]() using mlx-vlm version **0.3.12**.
|
| 12 |
+
Refer to the [original model card](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) for more details on the model.
|
| 13 |
+
## Use with mlx
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
```bash
|
| 16 |
+
pip install -U mlx-vlm
|
| 17 |
```
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
```bash
|
| 20 |
+
python -m mlx_vlm.generate --model mlx-community/Qwen3.5-397B-A17B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
```
|
config.json
CHANGED
|
@@ -11,972 +11,12 @@
|
|
| 11 |
"quantization": {
|
| 12 |
"group_size": 64,
|
| 13 |
"bits": 4,
|
| 14 |
-
"mode": "affine"
|
| 15 |
-
"language_model.model.layers.0.mlp.gate": {
|
| 16 |
-
"group_size": 64,
|
| 17 |
-
"bits": 8
|
| 18 |
-
},
|
| 19 |
-
"language_model.model.layers.0.mlp.shared_expert_gate": {
|
| 20 |
-
"group_size": 64,
|
| 21 |
-
"bits": 8
|
| 22 |
-
},
|
| 23 |
-
"language_model.model.layers.1.mlp.gate": {
|
| 24 |
-
"group_size": 64,
|
| 25 |
-
"bits": 8
|
| 26 |
-
},
|
| 27 |
-
"language_model.model.layers.1.mlp.shared_expert_gate": {
|
| 28 |
-
"group_size": 64,
|
| 29 |
-
"bits": 8
|
| 30 |
-
},
|
| 31 |
-
"language_model.model.layers.2.mlp.gate": {
|
| 32 |
-
"group_size": 64,
|
| 33 |
-
"bits": 8
|
| 34 |
-
},
|
| 35 |
-
"language_model.model.layers.2.mlp.shared_expert_gate": {
|
| 36 |
-
"group_size": 64,
|
| 37 |
-
"bits": 8
|
| 38 |
-
},
|
| 39 |
-
"language_model.model.layers.3.mlp.gate": {
|
| 40 |
-
"group_size": 64,
|
| 41 |
-
"bits": 8
|
| 42 |
-
},
|
| 43 |
-
"language_model.model.layers.3.mlp.shared_expert_gate": {
|
| 44 |
-
"group_size": 64,
|
| 45 |
-
"bits": 8
|
| 46 |
-
},
|
| 47 |
-
"language_model.model.layers.4.mlp.gate": {
|
| 48 |
-
"group_size": 64,
|
| 49 |
-
"bits": 8
|
| 50 |
-
},
|
| 51 |
-
"language_model.model.layers.4.mlp.shared_expert_gate": {
|
| 52 |
-
"group_size": 64,
|
| 53 |
-
"bits": 8
|
| 54 |
-
},
|
| 55 |
-
"language_model.model.layers.5.mlp.gate": {
|
| 56 |
-
"group_size": 64,
|
| 57 |
-
"bits": 8
|
| 58 |
-
},
|
| 59 |
-
"language_model.model.layers.5.mlp.shared_expert_gate": {
|
| 60 |
-
"group_size": 64,
|
| 61 |
-
"bits": 8
|
| 62 |
-
},
|
| 63 |
-
"language_model.model.layers.6.mlp.gate": {
|
| 64 |
-
"group_size": 64,
|
| 65 |
-
"bits": 8
|
| 66 |
-
},
|
| 67 |
-
"language_model.model.layers.6.mlp.shared_expert_gate": {
|
| 68 |
-
"group_size": 64,
|
| 69 |
-
"bits": 8
|
| 70 |
-
},
|
| 71 |
-
"language_model.model.layers.7.mlp.gate": {
|
| 72 |
-
"group_size": 64,
|
| 73 |
-
"bits": 8
|
| 74 |
-
},
|
| 75 |
-
"language_model.model.layers.7.mlp.shared_expert_gate": {
|
| 76 |
-
"group_size": 64,
|
| 77 |
-
"bits": 8
|
| 78 |
-
},
|
| 79 |
-
"language_model.model.layers.8.mlp.gate": {
|
| 80 |
-
"group_size": 64,
|
| 81 |
-
"bits": 8
|
| 82 |
-
},
|
| 83 |
-
"language_model.model.layers.8.mlp.shared_expert_gate": {
|
| 84 |
-
"group_size": 64,
|
| 85 |
-
"bits": 8
|
| 86 |
-
},
|
| 87 |
-
"language_model.model.layers.9.mlp.gate": {
|
| 88 |
-
"group_size": 64,
|
| 89 |
-
"bits": 8
|
| 90 |
-
},
|
| 91 |
-
"language_model.model.layers.9.mlp.shared_expert_gate": {
|
| 92 |
-
"group_size": 64,
|
| 93 |
-
"bits": 8
|
| 94 |
-
},
|
| 95 |
-
"language_model.model.layers.10.mlp.gate": {
|
| 96 |
-
"group_size": 64,
|
| 97 |
-
"bits": 8
|
| 98 |
-
},
|
| 99 |
-
"language_model.model.layers.10.mlp.shared_expert_gate": {
|
| 100 |
-
"group_size": 64,
|
| 101 |
-
"bits": 8
|
| 102 |
-
},
|
| 103 |
-
"language_model.model.layers.11.mlp.gate": {
|
| 104 |
-
"group_size": 64,
|
| 105 |
-
"bits": 8
|
| 106 |
-
},
|
| 107 |
-
"language_model.model.layers.11.mlp.shared_expert_gate": {
|
| 108 |
-
"group_size": 64,
|
| 109 |
-
"bits": 8
|
| 110 |
-
},
|
| 111 |
-
"language_model.model.layers.12.mlp.gate": {
|
| 112 |
-
"group_size": 64,
|
| 113 |
-
"bits": 8
|
| 114 |
-
},
|
| 115 |
-
"language_model.model.layers.12.mlp.shared_expert_gate": {
|
| 116 |
-
"group_size": 64,
|
| 117 |
-
"bits": 8
|
| 118 |
-
},
|
| 119 |
-
"language_model.model.layers.13.mlp.gate": {
|
| 120 |
-
"group_size": 64,
|
| 121 |
-
"bits": 8
|
| 122 |
-
},
|
| 123 |
-
"language_model.model.layers.13.mlp.shared_expert_gate": {
|
| 124 |
-
"group_size": 64,
|
| 125 |
-
"bits": 8
|
| 126 |
-
},
|
| 127 |
-
"language_model.model.layers.14.mlp.gate": {
|
| 128 |
-
"group_size": 64,
|
| 129 |
-
"bits": 8
|
| 130 |
-
},
|
| 131 |
-
"language_model.model.layers.14.mlp.shared_expert_gate": {
|
| 132 |
-
"group_size": 64,
|
| 133 |
-
"bits": 8
|
| 134 |
-
},
|
| 135 |
-
"language_model.model.layers.15.mlp.gate": {
|
| 136 |
-
"group_size": 64,
|
| 137 |
-
"bits": 8
|
| 138 |
-
},
|
| 139 |
-
"language_model.model.layers.15.mlp.shared_expert_gate": {
|
| 140 |
-
"group_size": 64,
|
| 141 |
-
"bits": 8
|
| 142 |
-
},
|
| 143 |
-
"language_model.model.layers.16.mlp.gate": {
|
| 144 |
-
"group_size": 64,
|
| 145 |
-
"bits": 8
|
| 146 |
-
},
|
| 147 |
-
"language_model.model.layers.16.mlp.shared_expert_gate": {
|
| 148 |
-
"group_size": 64,
|
| 149 |
-
"bits": 8
|
| 150 |
-
},
|
| 151 |
-
"language_model.model.layers.17.mlp.gate": {
|
| 152 |
-
"group_size": 64,
|
| 153 |
-
"bits": 8
|
| 154 |
-
},
|
| 155 |
-
"language_model.model.layers.17.mlp.shared_expert_gate": {
|
| 156 |
-
"group_size": 64,
|
| 157 |
-
"bits": 8
|
| 158 |
-
},
|
| 159 |
-
"language_model.model.layers.18.mlp.gate": {
|
| 160 |
-
"group_size": 64,
|
| 161 |
-
"bits": 8
|
| 162 |
-
},
|
| 163 |
-
"language_model.model.layers.18.mlp.shared_expert_gate": {
|
| 164 |
-
"group_size": 64,
|
| 165 |
-
"bits": 8
|
| 166 |
-
},
|
| 167 |
-
"language_model.model.layers.19.mlp.gate": {
|
| 168 |
-
"group_size": 64,
|
| 169 |
-
"bits": 8
|
| 170 |
-
},
|
| 171 |
-
"language_model.model.layers.19.mlp.shared_expert_gate": {
|
| 172 |
-
"group_size": 64,
|
| 173 |
-
"bits": 8
|
| 174 |
-
},
|
| 175 |
-
"language_model.model.layers.20.mlp.gate": {
|
| 176 |
-
"group_size": 64,
|
| 177 |
-
"bits": 8
|
| 178 |
-
},
|
| 179 |
-
"language_model.model.layers.20.mlp.shared_expert_gate": {
|
| 180 |
-
"group_size": 64,
|
| 181 |
-
"bits": 8
|
| 182 |
-
},
|
| 183 |
-
"language_model.model.layers.21.mlp.gate": {
|
| 184 |
-
"group_size": 64,
|
| 185 |
-
"bits": 8
|
| 186 |
-
},
|
| 187 |
-
"language_model.model.layers.21.mlp.shared_expert_gate": {
|
| 188 |
-
"group_size": 64,
|
| 189 |
-
"bits": 8
|
| 190 |
-
},
|
| 191 |
-
"language_model.model.layers.22.mlp.gate": {
|
| 192 |
-
"group_size": 64,
|
| 193 |
-
"bits": 8
|
| 194 |
-
},
|
| 195 |
-
"language_model.model.layers.22.mlp.shared_expert_gate": {
|
| 196 |
-
"group_size": 64,
|
| 197 |
-
"bits": 8
|
| 198 |
-
},
|
| 199 |
-
"language_model.model.layers.23.mlp.gate": {
|
| 200 |
-
"group_size": 64,
|
| 201 |
-
"bits": 8
|
| 202 |
-
},
|
| 203 |
-
"language_model.model.layers.23.mlp.shared_expert_gate": {
|
| 204 |
-
"group_size": 64,
|
| 205 |
-
"bits": 8
|
| 206 |
-
},
|
| 207 |
-
"language_model.model.layers.24.mlp.gate": {
|
| 208 |
-
"group_size": 64,
|
| 209 |
-
"bits": 8
|
| 210 |
-
},
|
| 211 |
-
"language_model.model.layers.24.mlp.shared_expert_gate": {
|
| 212 |
-
"group_size": 64,
|
| 213 |
-
"bits": 8
|
| 214 |
-
},
|
| 215 |
-
"language_model.model.layers.25.mlp.gate": {
|
| 216 |
-
"group_size": 64,
|
| 217 |
-
"bits": 8
|
| 218 |
-
},
|
| 219 |
-
"language_model.model.layers.25.mlp.shared_expert_gate": {
|
| 220 |
-
"group_size": 64,
|
| 221 |
-
"bits": 8
|
| 222 |
-
},
|
| 223 |
-
"language_model.model.layers.26.mlp.gate": {
|
| 224 |
-
"group_size": 64,
|
| 225 |
-
"bits": 8
|
| 226 |
-
},
|
| 227 |
-
"language_model.model.layers.26.mlp.shared_expert_gate": {
|
| 228 |
-
"group_size": 64,
|
| 229 |
-
"bits": 8
|
| 230 |
-
},
|
| 231 |
-
"language_model.model.layers.27.mlp.gate": {
|
| 232 |
-
"group_size": 64,
|
| 233 |
-
"bits": 8
|
| 234 |
-
},
|
| 235 |
-
"language_model.model.layers.27.mlp.shared_expert_gate": {
|
| 236 |
-
"group_size": 64,
|
| 237 |
-
"bits": 8
|
| 238 |
-
},
|
| 239 |
-
"language_model.model.layers.28.mlp.gate": {
|
| 240 |
-
"group_size": 64,
|
| 241 |
-
"bits": 8
|
| 242 |
-
},
|
| 243 |
-
"language_model.model.layers.28.mlp.shared_expert_gate": {
|
| 244 |
-
"group_size": 64,
|
| 245 |
-
"bits": 8
|
| 246 |
-
},
|
| 247 |
-
"language_model.model.layers.29.mlp.gate": {
|
| 248 |
-
"group_size": 64,
|
| 249 |
-
"bits": 8
|
| 250 |
-
},
|
| 251 |
-
"language_model.model.layers.29.mlp.shared_expert_gate": {
|
| 252 |
-
"group_size": 64,
|
| 253 |
-
"bits": 8
|
| 254 |
-
},
|
| 255 |
-
"language_model.model.layers.30.mlp.gate": {
|
| 256 |
-
"group_size": 64,
|
| 257 |
-
"bits": 8
|
| 258 |
-
},
|
| 259 |
-
"language_model.model.layers.30.mlp.shared_expert_gate": {
|
| 260 |
-
"group_size": 64,
|
| 261 |
-
"bits": 8
|
| 262 |
-
},
|
| 263 |
-
"language_model.model.layers.31.mlp.gate": {
|
| 264 |
-
"group_size": 64,
|
| 265 |
-
"bits": 8
|
| 266 |
-
},
|
| 267 |
-
"language_model.model.layers.31.mlp.shared_expert_gate": {
|
| 268 |
-
"group_size": 64,
|
| 269 |
-
"bits": 8
|
| 270 |
-
},
|
| 271 |
-
"language_model.model.layers.32.mlp.gate": {
|
| 272 |
-
"group_size": 64,
|
| 273 |
-
"bits": 8
|
| 274 |
-
},
|
| 275 |
-
"language_model.model.layers.32.mlp.shared_expert_gate": {
|
| 276 |
-
"group_size": 64,
|
| 277 |
-
"bits": 8
|
| 278 |
-
},
|
| 279 |
-
"language_model.model.layers.33.mlp.gate": {
|
| 280 |
-
"group_size": 64,
|
| 281 |
-
"bits": 8
|
| 282 |
-
},
|
| 283 |
-
"language_model.model.layers.33.mlp.shared_expert_gate": {
|
| 284 |
-
"group_size": 64,
|
| 285 |
-
"bits": 8
|
| 286 |
-
},
|
| 287 |
-
"language_model.model.layers.34.mlp.gate": {
|
| 288 |
-
"group_size": 64,
|
| 289 |
-
"bits": 8
|
| 290 |
-
},
|
| 291 |
-
"language_model.model.layers.34.mlp.shared_expert_gate": {
|
| 292 |
-
"group_size": 64,
|
| 293 |
-
"bits": 8
|
| 294 |
-
},
|
| 295 |
-
"language_model.model.layers.35.mlp.gate": {
|
| 296 |
-
"group_size": 64,
|
| 297 |
-
"bits": 8
|
| 298 |
-
},
|
| 299 |
-
"language_model.model.layers.35.mlp.shared_expert_gate": {
|
| 300 |
-
"group_size": 64,
|
| 301 |
-
"bits": 8
|
| 302 |
-
},
|
| 303 |
-
"language_model.model.layers.36.mlp.gate": {
|
| 304 |
-
"group_size": 64,
|
| 305 |
-
"bits": 8
|
| 306 |
-
},
|
| 307 |
-
"language_model.model.layers.36.mlp.shared_expert_gate": {
|
| 308 |
-
"group_size": 64,
|
| 309 |
-
"bits": 8
|
| 310 |
-
},
|
| 311 |
-
"language_model.model.layers.37.mlp.gate": {
|
| 312 |
-
"group_size": 64,
|
| 313 |
-
"bits": 8
|
| 314 |
-
},
|
| 315 |
-
"language_model.model.layers.37.mlp.shared_expert_gate": {
|
| 316 |
-
"group_size": 64,
|
| 317 |
-
"bits": 8
|
| 318 |
-
},
|
| 319 |
-
"language_model.model.layers.38.mlp.gate": {
|
| 320 |
-
"group_size": 64,
|
| 321 |
-
"bits": 8
|
| 322 |
-
},
|
| 323 |
-
"language_model.model.layers.38.mlp.shared_expert_gate": {
|
| 324 |
-
"group_size": 64,
|
| 325 |
-
"bits": 8
|
| 326 |
-
},
|
| 327 |
-
"language_model.model.layers.39.mlp.gate": {
|
| 328 |
-
"group_size": 64,
|
| 329 |
-
"bits": 8
|
| 330 |
-
},
|
| 331 |
-
"language_model.model.layers.39.mlp.shared_expert_gate": {
|
| 332 |
-
"group_size": 64,
|
| 333 |
-
"bits": 8
|
| 334 |
-
},
|
| 335 |
-
"language_model.model.layers.40.mlp.gate": {
|
| 336 |
-
"group_size": 64,
|
| 337 |
-
"bits": 8
|
| 338 |
-
},
|
| 339 |
-
"language_model.model.layers.40.mlp.shared_expert_gate": {
|
| 340 |
-
"group_size": 64,
|
| 341 |
-
"bits": 8
|
| 342 |
-
},
|
| 343 |
-
"language_model.model.layers.41.mlp.gate": {
|
| 344 |
-
"group_size": 64,
|
| 345 |
-
"bits": 8
|
| 346 |
-
},
|
| 347 |
-
"language_model.model.layers.41.mlp.shared_expert_gate": {
|
| 348 |
-
"group_size": 64,
|
| 349 |
-
"bits": 8
|
| 350 |
-
},
|
| 351 |
-
"language_model.model.layers.42.mlp.gate": {
|
| 352 |
-
"group_size": 64,
|
| 353 |
-
"bits": 8
|
| 354 |
-
},
|
| 355 |
-
"language_model.model.layers.42.mlp.shared_expert_gate": {
|
| 356 |
-
"group_size": 64,
|
| 357 |
-
"bits": 8
|
| 358 |
-
},
|
| 359 |
-
"language_model.model.layers.43.mlp.gate": {
|
| 360 |
-
"group_size": 64,
|
| 361 |
-
"bits": 8
|
| 362 |
-
},
|
| 363 |
-
"language_model.model.layers.43.mlp.shared_expert_gate": {
|
| 364 |
-
"group_size": 64,
|
| 365 |
-
"bits": 8
|
| 366 |
-
},
|
| 367 |
-
"language_model.model.layers.44.mlp.gate": {
|
| 368 |
-
"group_size": 64,
|
| 369 |
-
"bits": 8
|
| 370 |
-
},
|
| 371 |
-
"language_model.model.layers.44.mlp.shared_expert_gate": {
|
| 372 |
-
"group_size": 64,
|
| 373 |
-
"bits": 8
|
| 374 |
-
},
|
| 375 |
-
"language_model.model.layers.45.mlp.gate": {
|
| 376 |
-
"group_size": 64,
|
| 377 |
-
"bits": 8
|
| 378 |
-
},
|
| 379 |
-
"language_model.model.layers.45.mlp.shared_expert_gate": {
|
| 380 |
-
"group_size": 64,
|
| 381 |
-
"bits": 8
|
| 382 |
-
},
|
| 383 |
-
"language_model.model.layers.46.mlp.gate": {
|
| 384 |
-
"group_size": 64,
|
| 385 |
-
"bits": 8
|
| 386 |
-
},
|
| 387 |
-
"language_model.model.layers.46.mlp.shared_expert_gate": {
|
| 388 |
-
"group_size": 64,
|
| 389 |
-
"bits": 8
|
| 390 |
-
},
|
| 391 |
-
"language_model.model.layers.47.mlp.gate": {
|
| 392 |
-
"group_size": 64,
|
| 393 |
-
"bits": 8
|
| 394 |
-
},
|
| 395 |
-
"language_model.model.layers.47.mlp.shared_expert_gate": {
|
| 396 |
-
"group_size": 64,
|
| 397 |
-
"bits": 8
|
| 398 |
-
},
|
| 399 |
-
"language_model.model.layers.48.mlp.gate": {
|
| 400 |
-
"group_size": 64,
|
| 401 |
-
"bits": 8
|
| 402 |
-
},
|
| 403 |
-
"language_model.model.layers.48.mlp.shared_expert_gate": {
|
| 404 |
-
"group_size": 64,
|
| 405 |
-
"bits": 8
|
| 406 |
-
},
|
| 407 |
-
"language_model.model.layers.49.mlp.gate": {
|
| 408 |
-
"group_size": 64,
|
| 409 |
-
"bits": 8
|
| 410 |
-
},
|
| 411 |
-
"language_model.model.layers.49.mlp.shared_expert_gate": {
|
| 412 |
-
"group_size": 64,
|
| 413 |
-
"bits": 8
|
| 414 |
-
},
|
| 415 |
-
"language_model.model.layers.50.mlp.gate": {
|
| 416 |
-
"group_size": 64,
|
| 417 |
-
"bits": 8
|
| 418 |
-
},
|
| 419 |
-
"language_model.model.layers.50.mlp.shared_expert_gate": {
|
| 420 |
-
"group_size": 64,
|
| 421 |
-
"bits": 8
|
| 422 |
-
},
|
| 423 |
-
"language_model.model.layers.51.mlp.gate": {
|
| 424 |
-
"group_size": 64,
|
| 425 |
-
"bits": 8
|
| 426 |
-
},
|
| 427 |
-
"language_model.model.layers.51.mlp.shared_expert_gate": {
|
| 428 |
-
"group_size": 64,
|
| 429 |
-
"bits": 8
|
| 430 |
-
},
|
| 431 |
-
"language_model.model.layers.52.mlp.gate": {
|
| 432 |
-
"group_size": 64,
|
| 433 |
-
"bits": 8
|
| 434 |
-
},
|
| 435 |
-
"language_model.model.layers.52.mlp.shared_expert_gate": {
|
| 436 |
-
"group_size": 64,
|
| 437 |
-
"bits": 8
|
| 438 |
-
},
|
| 439 |
-
"language_model.model.layers.53.mlp.gate": {
|
| 440 |
-
"group_size": 64,
|
| 441 |
-
"bits": 8
|
| 442 |
-
},
|
| 443 |
-
"language_model.model.layers.53.mlp.shared_expert_gate": {
|
| 444 |
-
"group_size": 64,
|
| 445 |
-
"bits": 8
|
| 446 |
-
},
|
| 447 |
-
"language_model.model.layers.54.mlp.gate": {
|
| 448 |
-
"group_size": 64,
|
| 449 |
-
"bits": 8
|
| 450 |
-
},
|
| 451 |
-
"language_model.model.layers.54.mlp.shared_expert_gate": {
|
| 452 |
-
"group_size": 64,
|
| 453 |
-
"bits": 8
|
| 454 |
-
},
|
| 455 |
-
"language_model.model.layers.55.mlp.gate": {
|
| 456 |
-
"group_size": 64,
|
| 457 |
-
"bits": 8
|
| 458 |
-
},
|
| 459 |
-
"language_model.model.layers.55.mlp.shared_expert_gate": {
|
| 460 |
-
"group_size": 64,
|
| 461 |
-
"bits": 8
|
| 462 |
-
},
|
| 463 |
-
"language_model.model.layers.56.mlp.gate": {
|
| 464 |
-
"group_size": 64,
|
| 465 |
-
"bits": 8
|
| 466 |
-
},
|
| 467 |
-
"language_model.model.layers.56.mlp.shared_expert_gate": {
|
| 468 |
-
"group_size": 64,
|
| 469 |
-
"bits": 8
|
| 470 |
-
},
|
| 471 |
-
"language_model.model.layers.57.mlp.gate": {
|
| 472 |
-
"group_size": 64,
|
| 473 |
-
"bits": 8
|
| 474 |
-
},
|
| 475 |
-
"language_model.model.layers.57.mlp.shared_expert_gate": {
|
| 476 |
-
"group_size": 64,
|
| 477 |
-
"bits": 8
|
| 478 |
-
},
|
| 479 |
-
"language_model.model.layers.58.mlp.gate": {
|
| 480 |
-
"group_size": 64,
|
| 481 |
-
"bits": 8
|
| 482 |
-
},
|
| 483 |
-
"language_model.model.layers.58.mlp.shared_expert_gate": {
|
| 484 |
-
"group_size": 64,
|
| 485 |
-
"bits": 8
|
| 486 |
-
},
|
| 487 |
-
"language_model.model.layers.59.mlp.gate": {
|
| 488 |
-
"group_size": 64,
|
| 489 |
-
"bits": 8
|
| 490 |
-
},
|
| 491 |
-
"language_model.model.layers.59.mlp.shared_expert_gate": {
|
| 492 |
-
"group_size": 64,
|
| 493 |
-
"bits": 8
|
| 494 |
-
}
|
| 495 |
},
|
| 496 |
"quantization_config": {
|
| 497 |
"group_size": 64,
|
| 498 |
"bits": 4,
|
| 499 |
-
"mode": "affine"
|
| 500 |
-
"language_model.model.layers.0.mlp.gate": {
|
| 501 |
-
"group_size": 64,
|
| 502 |
-
"bits": 8
|
| 503 |
-
},
|
| 504 |
-
"language_model.model.layers.0.mlp.shared_expert_gate": {
|
| 505 |
-
"group_size": 64,
|
| 506 |
-
"bits": 8
|
| 507 |
-
},
|
| 508 |
-
"language_model.model.layers.1.mlp.gate": {
|
| 509 |
-
"group_size": 64,
|
| 510 |
-
"bits": 8
|
| 511 |
-
},
|
| 512 |
-
"language_model.model.layers.1.mlp.shared_expert_gate": {
|
| 513 |
-
"group_size": 64,
|
| 514 |
-
"bits": 8
|
| 515 |
-
},
|
| 516 |
-
"language_model.model.layers.2.mlp.gate": {
|
| 517 |
-
"group_size": 64,
|
| 518 |
-
"bits": 8
|
| 519 |
-
},
|
| 520 |
-
"language_model.model.layers.2.mlp.shared_expert_gate": {
|
| 521 |
-
"group_size": 64,
|
| 522 |
-
"bits": 8
|
| 523 |
-
},
|
| 524 |
-
"language_model.model.layers.3.mlp.gate": {
|
| 525 |
-
"group_size": 64,
|
| 526 |
-
"bits": 8
|
| 527 |
-
},
|
| 528 |
-
"language_model.model.layers.3.mlp.shared_expert_gate": {
|
| 529 |
-
"group_size": 64,
|
| 530 |
-
"bits": 8
|
| 531 |
-
},
|
| 532 |
-
"language_model.model.layers.4.mlp.gate": {
|
| 533 |
-
"group_size": 64,
|
| 534 |
-
"bits": 8
|
| 535 |
-
},
|
| 536 |
-
"language_model.model.layers.4.mlp.shared_expert_gate": {
|
| 537 |
-
"group_size": 64,
|
| 538 |
-
"bits": 8
|
| 539 |
-
},
|
| 540 |
-
"language_model.model.layers.5.mlp.gate": {
|
| 541 |
-
"group_size": 64,
|
| 542 |
-
"bits": 8
|
| 543 |
-
},
|
| 544 |
-
"language_model.model.layers.5.mlp.shared_expert_gate": {
|
| 545 |
-
"group_size": 64,
|
| 546 |
-
"bits": 8
|
| 547 |
-
},
|
| 548 |
-
"language_model.model.layers.6.mlp.gate": {
|
| 549 |
-
"group_size": 64,
|
| 550 |
-
"bits": 8
|
| 551 |
-
},
|
| 552 |
-
"language_model.model.layers.6.mlp.shared_expert_gate": {
|
| 553 |
-
"group_size": 64,
|
| 554 |
-
"bits": 8
|
| 555 |
-
},
|
| 556 |
-
"language_model.model.layers.7.mlp.gate": {
|
| 557 |
-
"group_size": 64,
|
| 558 |
-
"bits": 8
|
| 559 |
-
},
|
| 560 |
-
"language_model.model.layers.7.mlp.shared_expert_gate": {
|
| 561 |
-
"group_size": 64,
|
| 562 |
-
"bits": 8
|
| 563 |
-
},
|
| 564 |
-
"language_model.model.layers.8.mlp.gate": {
|
| 565 |
-
"group_size": 64,
|
| 566 |
-
"bits": 8
|
| 567 |
-
},
|
| 568 |
-
"language_model.model.layers.8.mlp.shared_expert_gate": {
|
| 569 |
-
"group_size": 64,
|
| 570 |
-
"bits": 8
|
| 571 |
-
},
|
| 572 |
-
"language_model.model.layers.9.mlp.gate": {
|
| 573 |
-
"group_size": 64,
|
| 574 |
-
"bits": 8
|
| 575 |
-
},
|
| 576 |
-
"language_model.model.layers.9.mlp.shared_expert_gate": {
|
| 577 |
-
"group_size": 64,
|
| 578 |
-
"bits": 8
|
| 579 |
-
},
|
| 580 |
-
"language_model.model.layers.10.mlp.gate": {
|
| 581 |
-
"group_size": 64,
|
| 582 |
-
"bits": 8
|
| 583 |
-
},
|
| 584 |
-
"language_model.model.layers.10.mlp.shared_expert_gate": {
|
| 585 |
-
"group_size": 64,
|
| 586 |
-
"bits": 8
|
| 587 |
-
},
|
| 588 |
-
"language_model.model.layers.11.mlp.gate": {
|
| 589 |
-
"group_size": 64,
|
| 590 |
-
"bits": 8
|
| 591 |
-
},
|
| 592 |
-
"language_model.model.layers.11.mlp.shared_expert_gate": {
|
| 593 |
-
"group_size": 64,
|
| 594 |
-
"bits": 8
|
| 595 |
-
},
|
| 596 |
-
"language_model.model.layers.12.mlp.gate": {
|
| 597 |
-
"group_size": 64,
|
| 598 |
-
"bits": 8
|
| 599 |
-
},
|
| 600 |
-
"language_model.model.layers.12.mlp.shared_expert_gate": {
|
| 601 |
-
"group_size": 64,
|
| 602 |
-
"bits": 8
|
| 603 |
-
},
|
| 604 |
-
"language_model.model.layers.13.mlp.gate": {
|
| 605 |
-
"group_size": 64,
|
| 606 |
-
"bits": 8
|
| 607 |
-
},
|
| 608 |
-
"language_model.model.layers.13.mlp.shared_expert_gate": {
|
| 609 |
-
"group_size": 64,
|
| 610 |
-
"bits": 8
|
| 611 |
-
},
|
| 612 |
-
"language_model.model.layers.14.mlp.gate": {
|
| 613 |
-
"group_size": 64,
|
| 614 |
-
"bits": 8
|
| 615 |
-
},
|
| 616 |
-
"language_model.model.layers.14.mlp.shared_expert_gate": {
|
| 617 |
-
"group_size": 64,
|
| 618 |
-
"bits": 8
|
| 619 |
-
},
|
| 620 |
-
"language_model.model.layers.15.mlp.gate": {
|
| 621 |
-
"group_size": 64,
|
| 622 |
-
"bits": 8
|
| 623 |
-
},
|
| 624 |
-
"language_model.model.layers.15.mlp.shared_expert_gate": {
|
| 625 |
-
"group_size": 64,
|
| 626 |
-
"bits": 8
|
| 627 |
-
},
|
| 628 |
-
"language_model.model.layers.16.mlp.gate": {
|
| 629 |
-
"group_size": 64,
|
| 630 |
-
"bits": 8
|
| 631 |
-
},
|
| 632 |
-
"language_model.model.layers.16.mlp.shared_expert_gate": {
|
| 633 |
-
"group_size": 64,
|
| 634 |
-
"bits": 8
|
| 635 |
-
},
|
| 636 |
-
"language_model.model.layers.17.mlp.gate": {
|
| 637 |
-
"group_size": 64,
|
| 638 |
-
"bits": 8
|
| 639 |
-
},
|
| 640 |
-
"language_model.model.layers.17.mlp.shared_expert_gate": {
|
| 641 |
-
"group_size": 64,
|
| 642 |
-
"bits": 8
|
| 643 |
-
},
|
| 644 |
-
"language_model.model.layers.18.mlp.gate": {
|
| 645 |
-
"group_size": 64,
|
| 646 |
-
"bits": 8
|
| 647 |
-
},
|
| 648 |
-
"language_model.model.layers.18.mlp.shared_expert_gate": {
|
| 649 |
-
"group_size": 64,
|
| 650 |
-
"bits": 8
|
| 651 |
-
},
|
| 652 |
-
"language_model.model.layers.19.mlp.gate": {
|
| 653 |
-
"group_size": 64,
|
| 654 |
-
"bits": 8
|
| 655 |
-
},
|
| 656 |
-
"language_model.model.layers.19.mlp.shared_expert_gate": {
|
| 657 |
-
"group_size": 64,
|
| 658 |
-
"bits": 8
|
| 659 |
-
},
|
| 660 |
-
"language_model.model.layers.20.mlp.gate": {
|
| 661 |
-
"group_size": 64,
|
| 662 |
-
"bits": 8
|
| 663 |
-
},
|
| 664 |
-
"language_model.model.layers.20.mlp.shared_expert_gate": {
|
| 665 |
-
"group_size": 64,
|
| 666 |
-
"bits": 8
|
| 667 |
-
},
|
| 668 |
-
"language_model.model.layers.21.mlp.gate": {
|
| 669 |
-
"group_size": 64,
|
| 670 |
-
"bits": 8
|
| 671 |
-
},
|
| 672 |
-
"language_model.model.layers.21.mlp.shared_expert_gate": {
|
| 673 |
-
"group_size": 64,
|
| 674 |
-
"bits": 8
|
| 675 |
-
},
|
| 676 |
-
"language_model.model.layers.22.mlp.gate": {
|
| 677 |
-
"group_size": 64,
|
| 678 |
-
"bits": 8
|
| 679 |
-
},
|
| 680 |
-
"language_model.model.layers.22.mlp.shared_expert_gate": {
|
| 681 |
-
"group_size": 64,
|
| 682 |
-
"bits": 8
|
| 683 |
-
},
|
| 684 |
-
"language_model.model.layers.23.mlp.gate": {
|
| 685 |
-
"group_size": 64,
|
| 686 |
-
"bits": 8
|
| 687 |
-
},
|
| 688 |
-
"language_model.model.layers.23.mlp.shared_expert_gate": {
|
| 689 |
-
"group_size": 64,
|
| 690 |
-
"bits": 8
|
| 691 |
-
},
|
| 692 |
-
"language_model.model.layers.24.mlp.gate": {
|
| 693 |
-
"group_size": 64,
|
| 694 |
-
"bits": 8
|
| 695 |
-
},
|
| 696 |
-
"language_model.model.layers.24.mlp.shared_expert_gate": {
|
| 697 |
-
"group_size": 64,
|
| 698 |
-
"bits": 8
|
| 699 |
-
},
|
| 700 |
-
"language_model.model.layers.25.mlp.gate": {
|
| 701 |
-
"group_size": 64,
|
| 702 |
-
"bits": 8
|
| 703 |
-
},
|
| 704 |
-
"language_model.model.layers.25.mlp.shared_expert_gate": {
|
| 705 |
-
"group_size": 64,
|
| 706 |
-
"bits": 8
|
| 707 |
-
},
|
| 708 |
-
"language_model.model.layers.26.mlp.gate": {
|
| 709 |
-
"group_size": 64,
|
| 710 |
-
"bits": 8
|
| 711 |
-
},
|
| 712 |
-
"language_model.model.layers.26.mlp.shared_expert_gate": {
|
| 713 |
-
"group_size": 64,
|
| 714 |
-
"bits": 8
|
| 715 |
-
},
|
| 716 |
-
"language_model.model.layers.27.mlp.gate": {
|
| 717 |
-
"group_size": 64,
|
| 718 |
-
"bits": 8
|
| 719 |
-
},
|
| 720 |
-
"language_model.model.layers.27.mlp.shared_expert_gate": {
|
| 721 |
-
"group_size": 64,
|
| 722 |
-
"bits": 8
|
| 723 |
-
},
|
| 724 |
-
"language_model.model.layers.28.mlp.gate": {
|
| 725 |
-
"group_size": 64,
|
| 726 |
-
"bits": 8
|
| 727 |
-
},
|
| 728 |
-
"language_model.model.layers.28.mlp.shared_expert_gate": {
|
| 729 |
-
"group_size": 64,
|
| 730 |
-
"bits": 8
|
| 731 |
-
},
|
| 732 |
-
"language_model.model.layers.29.mlp.gate": {
|
| 733 |
-
"group_size": 64,
|
| 734 |
-
"bits": 8
|
| 735 |
-
},
|
| 736 |
-
"language_model.model.layers.29.mlp.shared_expert_gate": {
|
| 737 |
-
"group_size": 64,
|
| 738 |
-
"bits": 8
|
| 739 |
-
},
|
| 740 |
-
"language_model.model.layers.30.mlp.gate": {
|
| 741 |
-
"group_size": 64,
|
| 742 |
-
"bits": 8
|
| 743 |
-
},
|
| 744 |
-
"language_model.model.layers.30.mlp.shared_expert_gate": {
|
| 745 |
-
"group_size": 64,
|
| 746 |
-
"bits": 8
|
| 747 |
-
},
|
| 748 |
-
"language_model.model.layers.31.mlp.gate": {
|
| 749 |
-
"group_size": 64,
|
| 750 |
-
"bits": 8
|
| 751 |
-
},
|
| 752 |
-
"language_model.model.layers.31.mlp.shared_expert_gate": {
|
| 753 |
-
"group_size": 64,
|
| 754 |
-
"bits": 8
|
| 755 |
-
},
|
| 756 |
-
"language_model.model.layers.32.mlp.gate": {
|
| 757 |
-
"group_size": 64,
|
| 758 |
-
"bits": 8
|
| 759 |
-
},
|
| 760 |
-
"language_model.model.layers.32.mlp.shared_expert_gate": {
|
| 761 |
-
"group_size": 64,
|
| 762 |
-
"bits": 8
|
| 763 |
-
},
|
| 764 |
-
"language_model.model.layers.33.mlp.gate": {
|
| 765 |
-
"group_size": 64,
|
| 766 |
-
"bits": 8
|
| 767 |
-
},
|
| 768 |
-
"language_model.model.layers.33.mlp.shared_expert_gate": {
|
| 769 |
-
"group_size": 64,
|
| 770 |
-
"bits": 8
|
| 771 |
-
},
|
| 772 |
-
"language_model.model.layers.34.mlp.gate": {
|
| 773 |
-
"group_size": 64,
|
| 774 |
-
"bits": 8
|
| 775 |
-
},
|
| 776 |
-
"language_model.model.layers.34.mlp.shared_expert_gate": {
|
| 777 |
-
"group_size": 64,
|
| 778 |
-
"bits": 8
|
| 779 |
-
},
|
| 780 |
-
"language_model.model.layers.35.mlp.gate": {
|
| 781 |
-
"group_size": 64,
|
| 782 |
-
"bits": 8
|
| 783 |
-
},
|
| 784 |
-
"language_model.model.layers.35.mlp.shared_expert_gate": {
|
| 785 |
-
"group_size": 64,
|
| 786 |
-
"bits": 8
|
| 787 |
-
},
|
| 788 |
-
"language_model.model.layers.36.mlp.gate": {
|
| 789 |
-
"group_size": 64,
|
| 790 |
-
"bits": 8
|
| 791 |
-
},
|
| 792 |
-
"language_model.model.layers.36.mlp.shared_expert_gate": {
|
| 793 |
-
"group_size": 64,
|
| 794 |
-
"bits": 8
|
| 795 |
-
},
|
| 796 |
-
"language_model.model.layers.37.mlp.gate": {
|
| 797 |
-
"group_size": 64,
|
| 798 |
-
"bits": 8
|
| 799 |
-
},
|
| 800 |
-
"language_model.model.layers.37.mlp.shared_expert_gate": {
|
| 801 |
-
"group_size": 64,
|
| 802 |
-
"bits": 8
|
| 803 |
-
},
|
| 804 |
-
"language_model.model.layers.38.mlp.gate": {
|
| 805 |
-
"group_size": 64,
|
| 806 |
-
"bits": 8
|
| 807 |
-
},
|
| 808 |
-
"language_model.model.layers.38.mlp.shared_expert_gate": {
|
| 809 |
-
"group_size": 64,
|
| 810 |
-
"bits": 8
|
| 811 |
-
},
|
| 812 |
-
"language_model.model.layers.39.mlp.gate": {
|
| 813 |
-
"group_size": 64,
|
| 814 |
-
"bits": 8
|
| 815 |
-
},
|
| 816 |
-
"language_model.model.layers.39.mlp.shared_expert_gate": {
|
| 817 |
-
"group_size": 64,
|
| 818 |
-
"bits": 8
|
| 819 |
-
},
|
| 820 |
-
"language_model.model.layers.40.mlp.gate": {
|
| 821 |
-
"group_size": 64,
|
| 822 |
-
"bits": 8
|
| 823 |
-
},
|
| 824 |
-
"language_model.model.layers.40.mlp.shared_expert_gate": {
|
| 825 |
-
"group_size": 64,
|
| 826 |
-
"bits": 8
|
| 827 |
-
},
|
| 828 |
-
"language_model.model.layers.41.mlp.gate": {
|
| 829 |
-
"group_size": 64,
|
| 830 |
-
"bits": 8
|
| 831 |
-
},
|
| 832 |
-
"language_model.model.layers.41.mlp.shared_expert_gate": {
|
| 833 |
-
"group_size": 64,
|
| 834 |
-
"bits": 8
|
| 835 |
-
},
|
| 836 |
-
"language_model.model.layers.42.mlp.gate": {
|
| 837 |
-
"group_size": 64,
|
| 838 |
-
"bits": 8
|
| 839 |
-
},
|
| 840 |
-
"language_model.model.layers.42.mlp.shared_expert_gate": {
|
| 841 |
-
"group_size": 64,
|
| 842 |
-
"bits": 8
|
| 843 |
-
},
|
| 844 |
-
"language_model.model.layers.43.mlp.gate": {
|
| 845 |
-
"group_size": 64,
|
| 846 |
-
"bits": 8
|
| 847 |
-
},
|
| 848 |
-
"language_model.model.layers.43.mlp.shared_expert_gate": {
|
| 849 |
-
"group_size": 64,
|
| 850 |
-
"bits": 8
|
| 851 |
-
},
|
| 852 |
-
"language_model.model.layers.44.mlp.gate": {
|
| 853 |
-
"group_size": 64,
|
| 854 |
-
"bits": 8
|
| 855 |
-
},
|
| 856 |
-
"language_model.model.layers.44.mlp.shared_expert_gate": {
|
| 857 |
-
"group_size": 64,
|
| 858 |
-
"bits": 8
|
| 859 |
-
},
|
| 860 |
-
"language_model.model.layers.45.mlp.gate": {
|
| 861 |
-
"group_size": 64,
|
| 862 |
-
"bits": 8
|
| 863 |
-
},
|
| 864 |
-
"language_model.model.layers.45.mlp.shared_expert_gate": {
|
| 865 |
-
"group_size": 64,
|
| 866 |
-
"bits": 8
|
| 867 |
-
},
|
| 868 |
-
"language_model.model.layers.46.mlp.gate": {
|
| 869 |
-
"group_size": 64,
|
| 870 |
-
"bits": 8
|
| 871 |
-
},
|
| 872 |
-
"language_model.model.layers.46.mlp.shared_expert_gate": {
|
| 873 |
-
"group_size": 64,
|
| 874 |
-
"bits": 8
|
| 875 |
-
},
|
| 876 |
-
"language_model.model.layers.47.mlp.gate": {
|
| 877 |
-
"group_size": 64,
|
| 878 |
-
"bits": 8
|
| 879 |
-
},
|
| 880 |
-
"language_model.model.layers.47.mlp.shared_expert_gate": {
|
| 881 |
-
"group_size": 64,
|
| 882 |
-
"bits": 8
|
| 883 |
-
},
|
| 884 |
-
"language_model.model.layers.48.mlp.gate": {
|
| 885 |
-
"group_size": 64,
|
| 886 |
-
"bits": 8
|
| 887 |
-
},
|
| 888 |
-
"language_model.model.layers.48.mlp.shared_expert_gate": {
|
| 889 |
-
"group_size": 64,
|
| 890 |
-
"bits": 8
|
| 891 |
-
},
|
| 892 |
-
"language_model.model.layers.49.mlp.gate": {
|
| 893 |
-
"group_size": 64,
|
| 894 |
-
"bits": 8
|
| 895 |
-
},
|
| 896 |
-
"language_model.model.layers.49.mlp.shared_expert_gate": {
|
| 897 |
-
"group_size": 64,
|
| 898 |
-
"bits": 8
|
| 899 |
-
},
|
| 900 |
-
"language_model.model.layers.50.mlp.gate": {
|
| 901 |
-
"group_size": 64,
|
| 902 |
-
"bits": 8
|
| 903 |
-
},
|
| 904 |
-
"language_model.model.layers.50.mlp.shared_expert_gate": {
|
| 905 |
-
"group_size": 64,
|
| 906 |
-
"bits": 8
|
| 907 |
-
},
|
| 908 |
-
"language_model.model.layers.51.mlp.gate": {
|
| 909 |
-
"group_size": 64,
|
| 910 |
-
"bits": 8
|
| 911 |
-
},
|
| 912 |
-
"language_model.model.layers.51.mlp.shared_expert_gate": {
|
| 913 |
-
"group_size": 64,
|
| 914 |
-
"bits": 8
|
| 915 |
-
},
|
| 916 |
-
"language_model.model.layers.52.mlp.gate": {
|
| 917 |
-
"group_size": 64,
|
| 918 |
-
"bits": 8
|
| 919 |
-
},
|
| 920 |
-
"language_model.model.layers.52.mlp.shared_expert_gate": {
|
| 921 |
-
"group_size": 64,
|
| 922 |
-
"bits": 8
|
| 923 |
-
},
|
| 924 |
-
"language_model.model.layers.53.mlp.gate": {
|
| 925 |
-
"group_size": 64,
|
| 926 |
-
"bits": 8
|
| 927 |
-
},
|
| 928 |
-
"language_model.model.layers.53.mlp.shared_expert_gate": {
|
| 929 |
-
"group_size": 64,
|
| 930 |
-
"bits": 8
|
| 931 |
-
},
|
| 932 |
-
"language_model.model.layers.54.mlp.gate": {
|
| 933 |
-
"group_size": 64,
|
| 934 |
-
"bits": 8
|
| 935 |
-
},
|
| 936 |
-
"language_model.model.layers.54.mlp.shared_expert_gate": {
|
| 937 |
-
"group_size": 64,
|
| 938 |
-
"bits": 8
|
| 939 |
-
},
|
| 940 |
-
"language_model.model.layers.55.mlp.gate": {
|
| 941 |
-
"group_size": 64,
|
| 942 |
-
"bits": 8
|
| 943 |
-
},
|
| 944 |
-
"language_model.model.layers.55.mlp.shared_expert_gate": {
|
| 945 |
-
"group_size": 64,
|
| 946 |
-
"bits": 8
|
| 947 |
-
},
|
| 948 |
-
"language_model.model.layers.56.mlp.gate": {
|
| 949 |
-
"group_size": 64,
|
| 950 |
-
"bits": 8
|
| 951 |
-
},
|
| 952 |
-
"language_model.model.layers.56.mlp.shared_expert_gate": {
|
| 953 |
-
"group_size": 64,
|
| 954 |
-
"bits": 8
|
| 955 |
-
},
|
| 956 |
-
"language_model.model.layers.57.mlp.gate": {
|
| 957 |
-
"group_size": 64,
|
| 958 |
-
"bits": 8
|
| 959 |
-
},
|
| 960 |
-
"language_model.model.layers.57.mlp.shared_expert_gate": {
|
| 961 |
-
"group_size": 64,
|
| 962 |
-
"bits": 8
|
| 963 |
-
},
|
| 964 |
-
"language_model.model.layers.58.mlp.gate": {
|
| 965 |
-
"group_size": 64,
|
| 966 |
-
"bits": 8
|
| 967 |
-
},
|
| 968 |
-
"language_model.model.layers.58.mlp.shared_expert_gate": {
|
| 969 |
-
"group_size": 64,
|
| 970 |
-
"bits": 8
|
| 971 |
-
},
|
| 972 |
-
"language_model.model.layers.59.mlp.gate": {
|
| 973 |
-
"group_size": 64,
|
| 974 |
-
"bits": 8
|
| 975 |
-
},
|
| 976 |
-
"language_model.model.layers.59.mlp.shared_expert_gate": {
|
| 977 |
-
"group_size": 64,
|
| 978 |
-
"bits": 8
|
| 979 |
-
}
|
| 980 |
},
|
| 981 |
"text_config": {
|
| 982 |
"attention_bias": false,
|
|
@@ -1080,14 +120,30 @@
|
|
| 1080 |
11,
|
| 1081 |
10
|
| 1082 |
],
|
|
|
|
| 1083 |
"rope_theta": 10000000,
|
| 1084 |
-
"partial_rotary_factor": 0.25
|
| 1085 |
-
"type": "default"
|
| 1086 |
}
|
| 1087 |
},
|
| 1088 |
"tie_word_embeddings": false,
|
| 1089 |
"transformers_version": "4.57.0.dev0",
|
| 1090 |
"video_token_id": 248057,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1091 |
"vision_end_token_id": 248054,
|
| 1092 |
"vision_start_token_id": 248053
|
| 1093 |
}
|
|
|
|
| 11 |
"quantization": {
|
| 12 |
"group_size": 64,
|
| 13 |
"bits": 4,
|
| 14 |
+
"mode": "affine"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
"quantization_config": {
|
| 17 |
"group_size": 64,
|
| 18 |
"bits": 4,
|
| 19 |
+
"mode": "affine"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
},
|
| 21 |
"text_config": {
|
| 22 |
"attention_bias": false,
|
|
|
|
| 120 |
11,
|
| 121 |
10
|
| 122 |
],
|
| 123 |
+
"rope_type": "default",
|
| 124 |
"rope_theta": 10000000,
|
| 125 |
+
"partial_rotary_factor": 0.25
|
|
|
|
| 126 |
}
|
| 127 |
},
|
| 128 |
"tie_word_embeddings": false,
|
| 129 |
"transformers_version": "4.57.0.dev0",
|
| 130 |
"video_token_id": 248057,
|
| 131 |
+
"vision_config": {
|
| 132 |
+
"deepstack_visual_indexes": [],
|
| 133 |
+
"depth": 27,
|
| 134 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 135 |
+
"hidden_size": 1152,
|
| 136 |
+
"in_channels": 3,
|
| 137 |
+
"initializer_range": 0.02,
|
| 138 |
+
"intermediate_size": 4304,
|
| 139 |
+
"model_type": "qwen3_5_moe",
|
| 140 |
+
"num_heads": 16,
|
| 141 |
+
"num_position_embeddings": 2304,
|
| 142 |
+
"out_hidden_size": 4096,
|
| 143 |
+
"patch_size": 16,
|
| 144 |
+
"spatial_merge_size": 2,
|
| 145 |
+
"temporal_patch_size": 2
|
| 146 |
+
},
|
| 147 |
"vision_end_token_id": 248054,
|
| 148 |
"vision_start_token_id": 248053
|
| 149 |
}
|
model-00001-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:361799676d080074e65b29ce20cae9cde05b56831c372d487ed4887b301b26a8
|
| 3 |
+
size 5250456685
|
model-00002-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b032c716ed386ef8ee090c1a1915b46c3c53b3899bca3be42cbd9885d4f991e8
|
| 3 |
+
size 4906575065
|
model-00003-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce73c3ca05a82486f4112e46a5fe80d965590c0527a5e6bd3b1fc2f0c95e3e5e
|
| 3 |
+
size 4899103668
|
model-00004-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:182b3b9461f573e73d4d27696346ca3634216234c113bf3ea7c2fda32a77fa6c
|
| 3 |
+
size 4981310204
|
model-00005-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8452e7513c569caece2916750d6adf22bf1a8fb17c1bd7e2de72197c905098d
|
| 3 |
+
size 4906575057
|
model-00006-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1647865d9f3a10eada5923056000a960c6c5c15d32b9e2fdaabfcc0498b984c7
|
| 3 |
+
size 4899103678
|
model-00007-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32246ab4ff7a98e06ad6c0be7dde31aae0e75665fe3cc9bc8aa55bda16f0fcbd
|
| 3 |
+
size 4981310146
|
model-00008-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9cf28f7d83015f239fdfd9a8f4570c0623a9b9eaf848d2ab174675c40302eb5
|
| 3 |
+
size 4906575110
|
model-00009-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:758f63d945a298653219c151ab8e474b587db4b8db29d08f1a17aafa1e845644
|
| 3 |
+
size 4899103709
|
model-00010-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fae3b1d52e103cac7bc7ada1db8d8513d5fe9131833b832256cc0fbbae2ad596
|
| 3 |
+
size 4981310282
|
model-00011-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6cfec296e8ce24e3782a56eb5bbba256eb0e9749a06806431870654476430a6
|
| 3 |
+
size 4906575161
|
model-00012-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46deac6ed7bf0f54dc32a0f7168cc3a63093847f0086fb375db7fbbfcd553185
|
| 3 |
+
size 4899103715
|
model-00013-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:727767e29695e06e7041570c070b3a89835ac7a5dcff3fc907e0722319f7bd3a
|
| 3 |
+
size 4981310244
|
model-00014-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c5b5666e91fa8424c69d85378faa92adb65d3682726f0e4c83b877bfff23544
|
| 3 |
+
size 4906575101
|
model-00015-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9b17bce9a5beb74ebede9dbe993abf2b435024fc3d63930959ccc7869553b73
|
| 3 |
+
size 4899103721
|
model-00016-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fd2152c2bd7e1344151b3364b64fe522bd27e7e461c5f422202cb3a5da4df3c
|
| 3 |
+
size 4981310260
|
model-00017-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41480b57a8f6675b750d286b80800ac56875055df06224fb6a62eb4f2497c8ed
|
| 3 |
+
size 4906575097
|
model-00018-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdcebab30ff3fbfd288efeb0ac582c35c98188689e267d020e365bdc88cf729c
|
| 3 |
+
size 4899103711
|
model-00019-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6948f546257ed4b09cf53782d36d193907e8ecf22f528729c66c66cbf09f2115
|
| 3 |
+
size 4981310264
|
model-00020-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f727102dd2c400483f56e319425c15a7b48ceabbf60515fba7a6f68bdc90a75f
|
| 3 |
+
size 4906575149
|
model-00021-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ce671cbba6e5a7d97513d08511269592b7f5f916375a75b4d4545b90a2c9822
|
| 3 |
+
size 4899103691
|
model-00022-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33ef1bc5e7658a63a38f8223d4adc889df80c6cfed4abe07709e1e2280f803f2
|
| 3 |
+
size 4981310258
|
model-00023-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca6c64a485e6c01aab595e35e30c5e4f6e58dc27d8d959fd3185d07bb3c5444d
|
| 3 |
+
size 4906575157
|
model-00024-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80a1f2a69d7ac8ba1d116ba9abb3627cd522b10f894170f829a750ce128b8885
|
| 3 |
+
size 4899103721
|
model-00025-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a57048a75c863b353b02c55ed61ac408e22d935db6bc4530f2cbdf75018d504c
|
| 3 |
+
size 4981310280
|
model-00026-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ad2519dce9ddfaa76f6a0379ba7c4f4549513fe7cd3310d94b74e0560417bf
|
| 3 |
+
size 4906575149
|
model-00027-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:407d0d0ef6d01fd5138538dd8badbcc59f13c3261277d75a12cb4185acc9c613
|
| 3 |
+
size 4899103721
|
model-00028-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bb4c6166f10203a29e309c9473b8d8a1929007ffc754770cdaec6fc6c9c5f7c
|
| 3 |
+
size 4981310254
|
model-00029-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:124c156fa19aeca7f721a88fc894b1bc7d36bf2f03c026c5698c0b76d947af06
|
| 3 |
+
size 4906575153
|
model-00030-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:562544a4d7d6203b1c0fe24aac470767f4564ba1399424d679be2af46bc00e6a
|
| 3 |
+
size 4899103705
|
model-00031-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b785e123019df25ff40009f2fb308d53307fd830765238003284f356e6ca387
|
| 3 |
+
size 4981310254
|
model-00032-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a09d9ad648fbb2ef4db5ef090a4bff11c5dd188920868d721514fd1e07f1ed
|
| 3 |
+
size 4906575089
|
model-00033-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8dca928a363a3e8e763ab11e622b59f09a940f44cc537d600a267403a9b8084
|
| 3 |
+
size 4899103717
|
model-00034-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90642ea0d7b03c10083682eefd2341b2d8b3630e845befe7e1344f0734cef0dd
|
| 3 |
+
size 4981310234
|
model-00035-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ca3580b7cf5fe11f3b18b1a0e1305493bee6a00a17b96dfbb53481a2c5017ea
|
| 3 |
+
size 4906575135
|
model-00036-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b08ef8225099efef7015208279301e0bc3613f524ff86177d22e320089036723
|
| 3 |
+
size 4899103651
|
model-00037-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2e70e7e4e1c66adcf3982307dee354852331eb80416207a65d64c986bde9a66
|
| 3 |
+
size 4981310256
|
model-00038-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1e2af6748394a0acee2c750cf8bcc88970014f3f9fa14bc891edb1c931fc4d2
|
| 3 |
+
size 4906575077
|
model-00039-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c58e1f29f2cb616a312f2bb05b9a6d6ca2da2ea953a6fd2228e7af5f0a0cfb6b
|
| 3 |
+
size 4899103717
|
model-00040-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02422272717572c7ce2c1eb4513103e9e688f2c8da52838f464d3f2a4c39eac9
|
| 3 |
+
size 4981310288
|
model-00041-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be64e70bdb7e383cae9a523b077127ab70098a697262498dc66f7cc7d4fc6017
|
| 3 |
+
size 4906575095
|
model-00042-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5083ca46270bf3ced3a025f47f9c11dccb7cd20a37890fb81e08f9d14f55c71d
|
| 3 |
+
size 4899103717
|
model-00043-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46cd310c0b15a95477097fe9943a66c5f3f26b629d215dad9e79b64eeeebdf5a
|
| 3 |
+
size 4981310246
|
model-00044-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:655e1157645305f0dd81ae64e55ee33cc387ead90c0f3a565011301318203bd0
|
| 3 |
+
size 4906575157
|
model-00045-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e78b2adc5bcca197eef3b96fdcb126f52c14d26e68ee9b994cf0e320329aaeaa
|
| 3 |
+
size 4899103721
|
model-00046-of-00046.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a008c67647f5487518fa7148905fbe2b4536c37c000fece03b322732daaa0ec
|
| 3 |
+
size 1787179741
|
model.safetensors.index.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
-
"total_parameters": 396346344576
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"language_model.lm_head.biases": "model-00046-of-00046.safetensors",
|
|
@@ -2635,6 +2634,339 @@
|
|
| 2635 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00008-of-00046.safetensors",
|
| 2636 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00008-of-00046.safetensors",
|
| 2637 |
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00007-of-00046.safetensors",
|
| 2638 |
-
"language_model.model.norm.weight": "model-00046-of-00046.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2639 |
}
|
| 2640 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 223860768352
|
|
|
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.biases": "model-00046-of-00046.safetensors",
|
|
|
|
| 2634 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00008-of-00046.safetensors",
|
| 2635 |
"language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00008-of-00046.safetensors",
|
| 2636 |
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00007-of-00046.safetensors",
|
| 2637 |
+
"language_model.model.norm.weight": "model-00046-of-00046.safetensors",
|
| 2638 |
+
"vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2639 |
+
"vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2640 |
+
"vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2641 |
+
"vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2642 |
+
"vision_tower.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2643 |
+
"vision_tower.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2644 |
+
"vision_tower.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2645 |
+
"vision_tower.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2646 |
+
"vision_tower.blocks.0.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2647 |
+
"vision_tower.blocks.0.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2648 |
+
"vision_tower.blocks.0.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2649 |
+
"vision_tower.blocks.0.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2650 |
+
"vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2651 |
+
"vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2652 |
+
"vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2653 |
+
"vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2654 |
+
"vision_tower.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2655 |
+
"vision_tower.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2656 |
+
"vision_tower.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2657 |
+
"vision_tower.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2658 |
+
"vision_tower.blocks.1.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2659 |
+
"vision_tower.blocks.1.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2660 |
+
"vision_tower.blocks.1.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2661 |
+
"vision_tower.blocks.1.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2662 |
+
"vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2663 |
+
"vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2664 |
+
"vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2665 |
+
"vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2666 |
+
"vision_tower.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2667 |
+
"vision_tower.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2668 |
+
"vision_tower.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2669 |
+
"vision_tower.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2670 |
+
"vision_tower.blocks.10.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2671 |
+
"vision_tower.blocks.10.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2672 |
+
"vision_tower.blocks.10.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2673 |
+
"vision_tower.blocks.10.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2674 |
+
"vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2675 |
+
"vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2676 |
+
"vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2677 |
+
"vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2678 |
+
"vision_tower.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2679 |
+
"vision_tower.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2680 |
+
"vision_tower.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2681 |
+
"vision_tower.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2682 |
+
"vision_tower.blocks.11.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2683 |
+
"vision_tower.blocks.11.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2684 |
+
"vision_tower.blocks.11.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2685 |
+
"vision_tower.blocks.11.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2686 |
+
"vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2687 |
+
"vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2688 |
+
"vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2689 |
+
"vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2690 |
+
"vision_tower.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2691 |
+
"vision_tower.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2692 |
+
"vision_tower.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2693 |
+
"vision_tower.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2694 |
+
"vision_tower.blocks.12.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2695 |
+
"vision_tower.blocks.12.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2696 |
+
"vision_tower.blocks.12.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2697 |
+
"vision_tower.blocks.12.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2698 |
+
"vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2699 |
+
"vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2700 |
+
"vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2701 |
+
"vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2702 |
+
"vision_tower.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2703 |
+
"vision_tower.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2704 |
+
"vision_tower.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2705 |
+
"vision_tower.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2706 |
+
"vision_tower.blocks.13.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2707 |
+
"vision_tower.blocks.13.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2708 |
+
"vision_tower.blocks.13.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2709 |
+
"vision_tower.blocks.13.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2710 |
+
"vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2711 |
+
"vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2712 |
+
"vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2713 |
+
"vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2714 |
+
"vision_tower.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2715 |
+
"vision_tower.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2716 |
+
"vision_tower.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2717 |
+
"vision_tower.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2718 |
+
"vision_tower.blocks.14.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2719 |
+
"vision_tower.blocks.14.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2720 |
+
"vision_tower.blocks.14.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2721 |
+
"vision_tower.blocks.14.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2722 |
+
"vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2723 |
+
"vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2724 |
+
"vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2725 |
+
"vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2726 |
+
"vision_tower.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2727 |
+
"vision_tower.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2728 |
+
"vision_tower.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2729 |
+
"vision_tower.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2730 |
+
"vision_tower.blocks.15.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2731 |
+
"vision_tower.blocks.15.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2732 |
+
"vision_tower.blocks.15.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2733 |
+
"vision_tower.blocks.15.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2734 |
+
"vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2735 |
+
"vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2736 |
+
"vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2737 |
+
"vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2738 |
+
"vision_tower.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2739 |
+
"vision_tower.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2740 |
+
"vision_tower.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2741 |
+
"vision_tower.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2742 |
+
"vision_tower.blocks.16.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2743 |
+
"vision_tower.blocks.16.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2744 |
+
"vision_tower.blocks.16.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2745 |
+
"vision_tower.blocks.16.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2746 |
+
"vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2747 |
+
"vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2748 |
+
"vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2749 |
+
"vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2750 |
+
"vision_tower.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2751 |
+
"vision_tower.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2752 |
+
"vision_tower.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2753 |
+
"vision_tower.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2754 |
+
"vision_tower.blocks.17.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2755 |
+
"vision_tower.blocks.17.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2756 |
+
"vision_tower.blocks.17.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2757 |
+
"vision_tower.blocks.17.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2758 |
+
"vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2759 |
+
"vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2760 |
+
"vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2761 |
+
"vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2762 |
+
"vision_tower.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2763 |
+
"vision_tower.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2764 |
+
"vision_tower.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2765 |
+
"vision_tower.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2766 |
+
"vision_tower.blocks.18.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2767 |
+
"vision_tower.blocks.18.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2768 |
+
"vision_tower.blocks.18.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2769 |
+
"vision_tower.blocks.18.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2770 |
+
"vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2771 |
+
"vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2772 |
+
"vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2773 |
+
"vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2774 |
+
"vision_tower.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2775 |
+
"vision_tower.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2776 |
+
"vision_tower.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2777 |
+
"vision_tower.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2778 |
+
"vision_tower.blocks.19.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2779 |
+
"vision_tower.blocks.19.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2780 |
+
"vision_tower.blocks.19.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2781 |
+
"vision_tower.blocks.19.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2782 |
+
"vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2783 |
+
"vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2784 |
+
"vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2785 |
+
"vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2786 |
+
"vision_tower.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2787 |
+
"vision_tower.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2788 |
+
"vision_tower.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2789 |
+
"vision_tower.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2790 |
+
"vision_tower.blocks.2.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2791 |
+
"vision_tower.blocks.2.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2792 |
+
"vision_tower.blocks.2.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2793 |
+
"vision_tower.blocks.2.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2794 |
+
"vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2795 |
+
"vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2796 |
+
"vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2797 |
+
"vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2798 |
+
"vision_tower.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2799 |
+
"vision_tower.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2800 |
+
"vision_tower.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2801 |
+
"vision_tower.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2802 |
+
"vision_tower.blocks.20.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2803 |
+
"vision_tower.blocks.20.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2804 |
+
"vision_tower.blocks.20.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2805 |
+
"vision_tower.blocks.20.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2806 |
+
"vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2807 |
+
"vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2808 |
+
"vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2809 |
+
"vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2810 |
+
"vision_tower.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2811 |
+
"vision_tower.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2812 |
+
"vision_tower.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2813 |
+
"vision_tower.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2814 |
+
"vision_tower.blocks.21.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2815 |
+
"vision_tower.blocks.21.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2816 |
+
"vision_tower.blocks.21.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2817 |
+
"vision_tower.blocks.21.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2818 |
+
"vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2819 |
+
"vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2820 |
+
"vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2821 |
+
"vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2822 |
+
"vision_tower.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2823 |
+
"vision_tower.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2824 |
+
"vision_tower.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2825 |
+
"vision_tower.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2826 |
+
"vision_tower.blocks.22.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2827 |
+
"vision_tower.blocks.22.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2828 |
+
"vision_tower.blocks.22.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2829 |
+
"vision_tower.blocks.22.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2830 |
+
"vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2831 |
+
"vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2832 |
+
"vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2833 |
+
"vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2834 |
+
"vision_tower.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2835 |
+
"vision_tower.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2836 |
+
"vision_tower.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2837 |
+
"vision_tower.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2838 |
+
"vision_tower.blocks.23.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2839 |
+
"vision_tower.blocks.23.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2840 |
+
"vision_tower.blocks.23.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2841 |
+
"vision_tower.blocks.23.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2842 |
+
"vision_tower.blocks.24.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2843 |
+
"vision_tower.blocks.24.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2844 |
+
"vision_tower.blocks.24.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2845 |
+
"vision_tower.blocks.24.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2846 |
+
"vision_tower.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2847 |
+
"vision_tower.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2848 |
+
"vision_tower.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2849 |
+
"vision_tower.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2850 |
+
"vision_tower.blocks.24.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2851 |
+
"vision_tower.blocks.24.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2852 |
+
"vision_tower.blocks.24.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2853 |
+
"vision_tower.blocks.24.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2854 |
+
"vision_tower.blocks.25.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2855 |
+
"vision_tower.blocks.25.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2856 |
+
"vision_tower.blocks.25.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2857 |
+
"vision_tower.blocks.25.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2858 |
+
"vision_tower.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2859 |
+
"vision_tower.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2860 |
+
"vision_tower.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2861 |
+
"vision_tower.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2862 |
+
"vision_tower.blocks.25.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2863 |
+
"vision_tower.blocks.25.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2864 |
+
"vision_tower.blocks.25.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2865 |
+
"vision_tower.blocks.25.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2866 |
+
"vision_tower.blocks.26.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2867 |
+
"vision_tower.blocks.26.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2868 |
+
"vision_tower.blocks.26.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2869 |
+
"vision_tower.blocks.26.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2870 |
+
"vision_tower.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2871 |
+
"vision_tower.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2872 |
+
"vision_tower.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2873 |
+
"vision_tower.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2874 |
+
"vision_tower.blocks.26.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2875 |
+
"vision_tower.blocks.26.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2876 |
+
"vision_tower.blocks.26.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2877 |
+
"vision_tower.blocks.26.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2878 |
+
"vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2879 |
+
"vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2880 |
+
"vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2881 |
+
"vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2882 |
+
"vision_tower.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2883 |
+
"vision_tower.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2884 |
+
"vision_tower.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2885 |
+
"vision_tower.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2886 |
+
"vision_tower.blocks.3.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2887 |
+
"vision_tower.blocks.3.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2888 |
+
"vision_tower.blocks.3.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2889 |
+
"vision_tower.blocks.3.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2890 |
+
"vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2891 |
+
"vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2892 |
+
"vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2893 |
+
"vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2894 |
+
"vision_tower.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2895 |
+
"vision_tower.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2896 |
+
"vision_tower.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2897 |
+
"vision_tower.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2898 |
+
"vision_tower.blocks.4.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2899 |
+
"vision_tower.blocks.4.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2900 |
+
"vision_tower.blocks.4.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2901 |
+
"vision_tower.blocks.4.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2902 |
+
"vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2903 |
+
"vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2904 |
+
"vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2905 |
+
"vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2906 |
+
"vision_tower.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2907 |
+
"vision_tower.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2908 |
+
"vision_tower.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2909 |
+
"vision_tower.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2910 |
+
"vision_tower.blocks.5.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2911 |
+
"vision_tower.blocks.5.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2912 |
+
"vision_tower.blocks.5.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2913 |
+
"vision_tower.blocks.5.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2914 |
+
"vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2915 |
+
"vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2916 |
+
"vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2917 |
+
"vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2918 |
+
"vision_tower.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2919 |
+
"vision_tower.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2920 |
+
"vision_tower.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2921 |
+
"vision_tower.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2922 |
+
"vision_tower.blocks.6.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2923 |
+
"vision_tower.blocks.6.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2924 |
+
"vision_tower.blocks.6.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2925 |
+
"vision_tower.blocks.6.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2926 |
+
"vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2927 |
+
"vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2928 |
+
"vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2929 |
+
"vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2930 |
+
"vision_tower.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2931 |
+
"vision_tower.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2932 |
+
"vision_tower.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2933 |
+
"vision_tower.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2934 |
+
"vision_tower.blocks.7.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2935 |
+
"vision_tower.blocks.7.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2936 |
+
"vision_tower.blocks.7.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2937 |
+
"vision_tower.blocks.7.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2938 |
+
"vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2939 |
+
"vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2940 |
+
"vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2941 |
+
"vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2942 |
+
"vision_tower.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2943 |
+
"vision_tower.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2944 |
+
"vision_tower.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2945 |
+
"vision_tower.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2946 |
+
"vision_tower.blocks.8.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2947 |
+
"vision_tower.blocks.8.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2948 |
+
"vision_tower.blocks.8.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2949 |
+
"vision_tower.blocks.8.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2950 |
+
"vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00046.safetensors",
|
| 2951 |
+
"vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00046.safetensors",
|
| 2952 |
+
"vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00046.safetensors",
|
| 2953 |
+
"vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00046.safetensors",
|
| 2954 |
+
"vision_tower.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2955 |
+
"vision_tower.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2956 |
+
"vision_tower.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2957 |
+
"vision_tower.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2958 |
+
"vision_tower.blocks.9.norm1.bias": "model-00001-of-00046.safetensors",
|
| 2959 |
+
"vision_tower.blocks.9.norm1.weight": "model-00001-of-00046.safetensors",
|
| 2960 |
+
"vision_tower.blocks.9.norm2.bias": "model-00001-of-00046.safetensors",
|
| 2961 |
+
"vision_tower.blocks.9.norm2.weight": "model-00001-of-00046.safetensors",
|
| 2962 |
+
"vision_tower.merger.linear_fc1.bias": "model-00001-of-00046.safetensors",
|
| 2963 |
+
"vision_tower.merger.linear_fc1.weight": "model-00001-of-00046.safetensors",
|
| 2964 |
+
"vision_tower.merger.linear_fc2.bias": "model-00001-of-00046.safetensors",
|
| 2965 |
+
"vision_tower.merger.linear_fc2.weight": "model-00001-of-00046.safetensors",
|
| 2966 |
+
"vision_tower.merger.norm.bias": "model-00001-of-00046.safetensors",
|
| 2967 |
+
"vision_tower.merger.norm.weight": "model-00001-of-00046.safetensors",
|
| 2968 |
+
"vision_tower.patch_embed.proj.bias": "model-00001-of-00046.safetensors",
|
| 2969 |
+
"vision_tower.patch_embed.proj.weight": "model-00001-of-00046.safetensors",
|
| 2970 |
+
"vision_tower.pos_embed.weight": "model-00001-of-00046.safetensors"
|
| 2971 |
}
|
| 2972 |
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|