Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +157 -3
- added_tokens.json +25 -0
- chat_template.jinja +7 -0
- config.json +171 -0
- configuration.py +190 -0
- convert_weights.py +78 -0
- generation_config.json +11 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +833 -0
- modeling.py +0 -0
- preprocessor_config.json +19 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +204 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,3 +1,157 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- Qwen/Qwen2.5-VL-3B-Instruct
|
| 7 |
+
tags:
|
| 8 |
+
- diffusion
|
| 9 |
+
- vlm
|
| 10 |
+
- block-diffusion
|
| 11 |
+
- parallel-decoding
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Fast-dVLM (3B) — Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
|
| 15 |
+
|
| 16 |
+
[[Paper](https://arxiv.org/abs/2604.06832)] [[Project Page](https://nvlabs.github.io/Fast-dLLM/fast_dvlm/)] [[Code](https://github.com/NVlabs/Fast-dLLM)] [[Fast-dLLM v2](https://huggingface.co/Efficient-Large-Model/Fast_dLLM_1.5B)]
|
| 17 |
+
|
| 18 |
+
## Introduction
|
| 19 |
+
|
| 20 |
+
Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in **physical AI scenarios** such as robotics and autonomous driving, where VLMs are deployed on edge devices at batch size one.
|
| 21 |
+
|
| 22 |
+
**Fast-dVLM** is a block-diffusion-based VLM that enables **KV-cache-compatible parallel decoding** and **speculative block decoding** for inference acceleration. Built on **Qwen2.5-VL-3B-Instruct**, Fast-dVLM directly converts the pretrained AR VLM into a block-diffusion model in a single stage, leveraging the already multimodally aligned VLM.
|
| 23 |
+
|
| 24 |
+
### Key Highlights
|
| 25 |
+
|
| 26 |
+
- **Lossless Quality**: Matches the AR baseline (Qwen2.5-VL-3B) across **11 multimodal benchmarks** (74.0 avg).
|
| 27 |
+
- **Up to 6.18x Speedup**: With SGLang integration and FP8 quantization.
|
| 28 |
+
- **2.63x Tokens/NFE**: With self-speculative block decoding.
|
| 29 |
+
- **Direct Conversion**: Single-stage AR-to-diffusion conversion outperforms two-stage approach (73.3 vs 60.2 avg).
|
| 30 |
+
|
| 31 |
+
### Key Techniques
|
| 32 |
+
|
| 33 |
+
- **Block-Size Annealing**: Curriculum that progressively increases the block size during training.
|
| 34 |
+
- **Causal Context Attention**: Noisy tokens attend bidirectionally within blocks (N2N), to clean tokens from preceding blocks (N2C), while clean tokens follow causal attention (C2C).
|
| 35 |
+
- **Auto-Truncation Masking**: Prevents cross-turn leakage in multi-turn dialogue.
|
| 36 |
+
- **Vision-Efficient Concatenation**: Vision embeddings included only in the clean stream, reducing peak memory by 15% and training time by 14.2%.
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
## Model Overview
|
| 41 |
+
|
| 42 |
+
| Property | Value |
|
| 43 |
+
|---|---|
|
| 44 |
+
| **Type** | Block Diffusion Vision-Language Model |
|
| 45 |
+
| **Base Model** | `Qwen/Qwen2.5-VL-3B-Instruct` |
|
| 46 |
+
| **Architecture** | Transformer w/ M-RoPE, SwiGLU, RMSNorm, GQA |
|
| 47 |
+
| **Text Layers** | 36 |
|
| 48 |
+
| **Vision Depth** | 32 |
|
| 49 |
+
| **Text Hidden Size** | 2048 |
|
| 50 |
+
| **Attention Heads** | 16 (Q), 2 (KV, GQA) |
|
| 51 |
+
| **Block Diffusion Size** | 32 |
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
## Quickstart
|
| 56 |
+
|
| 57 |
+
```python
|
| 58 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor
|
| 59 |
+
from qwen_vl_utils import process_vision_info
|
| 60 |
+
|
| 61 |
+
model_name = "Efficient-Large-Model/Fast_dVLM_3B"
|
| 62 |
+
|
| 63 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 64 |
+
model_name,
|
| 65 |
+
torch_dtype="auto",
|
| 66 |
+
device_map="auto",
|
| 67 |
+
trust_remote_code=True,
|
| 68 |
+
)
|
| 69 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 70 |
+
processor = AutoProcessor.from_pretrained(model_name, use_fast=False)
|
| 71 |
+
processor.tokenizer = tokenizer
|
| 72 |
+
|
| 73 |
+
prompt = "Describe this image in detail."
|
| 74 |
+
messages = [
|
| 75 |
+
{
|
| 76 |
+
"role": "user",
|
| 77 |
+
"content": [
|
| 78 |
+
{"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
|
| 79 |
+
{"type": "text", "text": prompt},
|
| 80 |
+
],
|
| 81 |
+
}
|
| 82 |
+
]
|
| 83 |
+
|
| 84 |
+
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 85 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 86 |
+
inputs = processor(
|
| 87 |
+
text=[text],
|
| 88 |
+
images=image_inputs,
|
| 89 |
+
videos=video_inputs,
|
| 90 |
+
padding=True,
|
| 91 |
+
return_tensors="pt",
|
| 92 |
+
).to(model.device)
|
| 93 |
+
|
| 94 |
+
mask_id = tokenizer.encode("|<MASK>|")[0]
|
| 95 |
+
|
| 96 |
+
generated_ids = model.generate(
|
| 97 |
+
input_ids=inputs.input_ids,
|
| 98 |
+
tokenizer=tokenizer,
|
| 99 |
+
pixel_values=inputs.pixel_values,
|
| 100 |
+
image_grid_thw=inputs.image_grid_thw,
|
| 101 |
+
mask_id=mask_id,
|
| 102 |
+
max_tokens=512,
|
| 103 |
+
)
|
| 104 |
+
|
| 105 |
+
generated_ids = [
|
| 106 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, generated_ids)
|
| 107 |
+
]
|
| 108 |
+
|
| 109 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 110 |
+
print(response)
|
| 111 |
+
```
|
| 112 |
+
|
| 113 |
+
---
|
| 114 |
+
|
| 115 |
+
## Benchmark Results
|
| 116 |
+
|
| 117 |
+
Fast-dVLM matches the AR baseline on 11 multimodal benchmarks while achieving 2.63x Tokens/NFE with speculative decoding.
|
| 118 |
+
|
| 119 |
+
| Model | AI2D | ChartQA | DocVQA | GQA | MMBench | MMMU | POPE | RWQA | SEED2+ | TextVQA | Avg | MMMU-Pro-V | Tok/NFE |
|
| 120 |
+
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 121 |
+
| Qwen2.5-VL-3B | 80.8 | 84.0 | 93.1 | 59.0 | 76.9 | 47.3 | 86.2 | 65.1 | 68.6 | 79.1 | 74.0 | 26.3 | 1.00 |
|
| 122 |
+
| **Fast-dVLM (MDM)** | 79.7 | 82.8 | 92.1 | 63.0 | 74.2 | 44.6 | 88.6 | 65.1 | 67.2 | 76.1 | 73.3 | 21.4 | 1.95 |
|
| 123 |
+
| **Fast-dVLM (spec.)** | 79.7 | 83.1 | 92.9 | 63.3 | 74.3 | 46.6 | 88.6 | 65.1 | 67.2 | 79.3 | **74.0** | 24.6 | **2.63** |
|
| 124 |
+
|
| 125 |
+
### Inference Acceleration
|
| 126 |
+
|
| 127 |
+
| Setting | MMMU-Pro-V | TPS | SpeedUp |
|
| 128 |
+
|---|---|---|---|
|
| 129 |
+
| AR baseline | 26.3 | 56.7 | 1.00x |
|
| 130 |
+
| Fast-dVLM (MDM, t=0.9) | 21.4 | 82.2 | 1.45x |
|
| 131 |
+
| + Spec. decoding (linear) | 24.6 | 112.7 | 1.98x |
|
| 132 |
+
| + SGLang serving | 24.1 | 319.0 | 5.63x |
|
| 133 |
+
| + SmoothQuant-W8A8 (FP8) | 23.8 | **350.3** | **6.18x** |
|
| 134 |
+
|
| 135 |
+
---
|
| 136 |
+
|
| 137 |
+
## Citation
|
| 138 |
+
|
| 139 |
+
If you use Fast-dVLM in your research, please cite:
|
| 140 |
+
|
| 141 |
+
```bibtex
|
| 142 |
+
@misc{wu2026fastdvlmefficientblockdiffusionvlm,
|
| 143 |
+
title={Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM},
|
| 144 |
+
author={Chengyue Wu and Shiyi Lan and Yonggan Fu and Sensen Gao and Jin Wang and Jincheng Yu and Jose M. Alvarez and Pavlo Molchanov and Ping Luo and Song Han and Ligeng Zhu and Enze Xie},
|
| 145 |
+
year={2026},
|
| 146 |
+
eprint={2604.06832},
|
| 147 |
+
archivePrefix={arXiv},
|
| 148 |
+
primaryClass={cs.CL},
|
| 149 |
+
url={https://arxiv.org/abs/2604.06832},
|
| 150 |
+
}
|
| 151 |
+
```
|
| 152 |
+
|
| 153 |
+
---
|
| 154 |
+
|
| 155 |
+
## License
|
| 156 |
+
|
| 157 |
+
Released under **Apache 2.0**, following the base Qwen2.5-VL license.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652,
|
| 24 |
+
"|<MASK>|": 151665
|
| 25 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"always_mask_im_end": true,
|
| 3 |
+
"anneal_block_size": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Fast_dVLMForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration.Fast_dVLMConfig",
|
| 10 |
+
"AutoModel": "modeling.Fast_dVLMForConditionalGeneration",
|
| 11 |
+
"AutoModelForCausalLM": "modeling.Fast_dVLMForConditionalGeneration"
|
| 12 |
+
},
|
| 13 |
+
"bd_size": 32,
|
| 14 |
+
"block_causal_no_dynamic": false,
|
| 15 |
+
"complementary_mask": true,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"enable_efficient_vision_embed": false,
|
| 18 |
+
"entropy_loss": false,
|
| 19 |
+
"entropy_loss_weight": 1.0,
|
| 20 |
+
"eos_token_id": 151645,
|
| 21 |
+
"flexible_bd_size": false,
|
| 22 |
+
"hidden_act": "silu",
|
| 23 |
+
"hidden_size": 2048,
|
| 24 |
+
"image_token_id": 151655,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 11008,
|
| 27 |
+
"max_position_embeddings": 128000,
|
| 28 |
+
"max_window_layers": 70,
|
| 29 |
+
"minimum_noise_level": 0.001,
|
| 30 |
+
"model_type": "fast_dvlm",
|
| 31 |
+
"num_attention_heads": 16,
|
| 32 |
+
"num_hidden_layers": 36,
|
| 33 |
+
"num_key_value_heads": 2,
|
| 34 |
+
"pad_token_id": 151643,
|
| 35 |
+
"rms_norm_eps": 1e-06,
|
| 36 |
+
"rope_scaling": {
|
| 37 |
+
"mrope_section": [
|
| 38 |
+
16,
|
| 39 |
+
24,
|
| 40 |
+
24
|
| 41 |
+
],
|
| 42 |
+
"rope_type": "default",
|
| 43 |
+
"type": "default"
|
| 44 |
+
},
|
| 45 |
+
"rope_theta": 1000000.0,
|
| 46 |
+
"sliding_window": 32768,
|
| 47 |
+
"text_config": {
|
| 48 |
+
"architectures": [
|
| 49 |
+
"Fast_dVLMForConditionalGeneration"
|
| 50 |
+
],
|
| 51 |
+
"attention_dropout": 0.0,
|
| 52 |
+
"auto_map": {
|
| 53 |
+
"AutoConfig": "configuration.Fast_dVLMConfig",
|
| 54 |
+
"AutoModel": "modeling.Fast_dVLMForConditionalGeneration",
|
| 55 |
+
"AutoModelForCausalLM": "modeling.Fast_dVLMForConditionalGeneration"
|
| 56 |
+
},
|
| 57 |
+
"bd_size": 8,
|
| 58 |
+
"block_causal_no_dynamic": false,
|
| 59 |
+
"bos_token_id": 151643,
|
| 60 |
+
"complementary_mask": true,
|
| 61 |
+
"dtype": "float32",
|
| 62 |
+
"entropy_loss": false,
|
| 63 |
+
"entropy_loss_weight": 1.0,
|
| 64 |
+
"eos_token_id": 151645,
|
| 65 |
+
"hidden_act": "silu",
|
| 66 |
+
"hidden_size": 2048,
|
| 67 |
+
"image_token_id": null,
|
| 68 |
+
"initializer_range": 0.02,
|
| 69 |
+
"intermediate_size": 11008,
|
| 70 |
+
"layer_types": [
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"full_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"full_attention",
|
| 83 |
+
"full_attention",
|
| 84 |
+
"full_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"full_attention",
|
| 88 |
+
"full_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"full_attention",
|
| 91 |
+
"full_attention",
|
| 92 |
+
"full_attention",
|
| 93 |
+
"full_attention",
|
| 94 |
+
"full_attention",
|
| 95 |
+
"full_attention",
|
| 96 |
+
"full_attention",
|
| 97 |
+
"full_attention",
|
| 98 |
+
"full_attention",
|
| 99 |
+
"full_attention",
|
| 100 |
+
"full_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"full_attention",
|
| 103 |
+
"full_attention",
|
| 104 |
+
"full_attention",
|
| 105 |
+
"full_attention",
|
| 106 |
+
"full_attention"
|
| 107 |
+
],
|
| 108 |
+
"max_position_embeddings": 128000,
|
| 109 |
+
"max_window_layers": 70,
|
| 110 |
+
"minimum_noise_level": 0.001,
|
| 111 |
+
"model_type": "fast_dvlm_for_causal_lm",
|
| 112 |
+
"num_attention_heads": 16,
|
| 113 |
+
"num_hidden_layers": 36,
|
| 114 |
+
"num_key_value_heads": 2,
|
| 115 |
+
"rms_norm_eps": 1e-06,
|
| 116 |
+
"rope_scaling": {
|
| 117 |
+
"mrope_section": [
|
| 118 |
+
16,
|
| 119 |
+
24,
|
| 120 |
+
24
|
| 121 |
+
],
|
| 122 |
+
"rope_type": "default",
|
| 123 |
+
"type": "default"
|
| 124 |
+
},
|
| 125 |
+
"rope_theta": 1000000.0,
|
| 126 |
+
"sliding_window": null,
|
| 127 |
+
"tie_word_embeddings": true,
|
| 128 |
+
"use_block_causal_mask": false,
|
| 129 |
+
"use_cache": true,
|
| 130 |
+
"use_sliding_window": false,
|
| 131 |
+
"video_token_id": null,
|
| 132 |
+
"vision_end_token_id": 151653,
|
| 133 |
+
"vision_start_token_id": 151652,
|
| 134 |
+
"vision_token_id": 151654,
|
| 135 |
+
"vocab_size": 151936
|
| 136 |
+
},
|
| 137 |
+
"transformers_version": "4.57.1",
|
| 138 |
+
"use_block_causal_mask": true,
|
| 139 |
+
"use_cache": true,
|
| 140 |
+
"use_sliding_window": false,
|
| 141 |
+
"video_token_id": 151656,
|
| 142 |
+
"vision_config": {
|
| 143 |
+
"depth": 32,
|
| 144 |
+
"dtype": "float32",
|
| 145 |
+
"fullatt_block_indexes": [
|
| 146 |
+
7,
|
| 147 |
+
15,
|
| 148 |
+
23,
|
| 149 |
+
31
|
| 150 |
+
],
|
| 151 |
+
"hidden_act": "silu",
|
| 152 |
+
"hidden_size": 1280,
|
| 153 |
+
"in_channels": 3,
|
| 154 |
+
"in_chans": 3,
|
| 155 |
+
"initializer_range": 0.02,
|
| 156 |
+
"intermediate_size": 3420,
|
| 157 |
+
"model_type": "fast_dvlm",
|
| 158 |
+
"num_heads": 16,
|
| 159 |
+
"out_hidden_size": 2048,
|
| 160 |
+
"patch_size": 14,
|
| 161 |
+
"spatial_merge_size": 2,
|
| 162 |
+
"spatial_patch_size": 14,
|
| 163 |
+
"temporal_patch_size": 2,
|
| 164 |
+
"tokens_per_second": 2,
|
| 165 |
+
"window_size": 112
|
| 166 |
+
},
|
| 167 |
+
"vision_end_token_id": 151653,
|
| 168 |
+
"vision_start_token_id": 151652,
|
| 169 |
+
"vision_token_id": 151654,
|
| 170 |
+
"vocab_size": 151936
|
| 171 |
+
}
|
configuration.py
ADDED
|
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# limitations under the License.
|
| 3 |
+
from transformers.configuration_utils import PretrainedConfig, layer_type_validation
|
| 4 |
+
from transformers.modeling_rope_utils import rope_config_validation
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
class Fast_dVLMVisionConfig(PretrainedConfig):
|
| 8 |
+
model_type = "fast_dvlm"
|
| 9 |
+
base_config_key = "vision_config"
|
| 10 |
+
|
| 11 |
+
def __init__(
|
| 12 |
+
self,
|
| 13 |
+
depth=32,
|
| 14 |
+
hidden_size=3584,
|
| 15 |
+
hidden_act="silu",
|
| 16 |
+
intermediate_size=3420,
|
| 17 |
+
num_heads=16,
|
| 18 |
+
in_channels=3,
|
| 19 |
+
patch_size=14,
|
| 20 |
+
spatial_merge_size=2,
|
| 21 |
+
temporal_patch_size=2,
|
| 22 |
+
tokens_per_second=4,
|
| 23 |
+
window_size=112,
|
| 24 |
+
out_hidden_size=3584,
|
| 25 |
+
fullatt_block_indexes=[7, 15, 23, 31],
|
| 26 |
+
initializer_range=0.02,
|
| 27 |
+
**kwargs,
|
| 28 |
+
):
|
| 29 |
+
super().__init__(**kwargs)
|
| 30 |
+
|
| 31 |
+
self.depth = depth
|
| 32 |
+
self.hidden_size = hidden_size
|
| 33 |
+
self.hidden_act = hidden_act
|
| 34 |
+
self.intermediate_size = intermediate_size
|
| 35 |
+
self.num_heads = num_heads
|
| 36 |
+
self.in_channels = in_channels
|
| 37 |
+
self.patch_size = patch_size
|
| 38 |
+
self.spatial_merge_size = spatial_merge_size
|
| 39 |
+
self.temporal_patch_size = temporal_patch_size
|
| 40 |
+
self.tokens_per_second = tokens_per_second
|
| 41 |
+
self.window_size = window_size
|
| 42 |
+
self.fullatt_block_indexes = fullatt_block_indexes
|
| 43 |
+
self.out_hidden_size = out_hidden_size
|
| 44 |
+
self.initializer_range = initializer_range
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
class Fast_dVLMTextConfig(PretrainedConfig):
|
| 48 |
+
|
| 49 |
+
model_type = "fast_dvlm_for_causal_lm"
|
| 50 |
+
base_config_key = "text_config"
|
| 51 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 52 |
+
base_model_tp_plan = {
|
| 53 |
+
"layers.*.self_attn.q_proj": "colwise",
|
| 54 |
+
"layers.*.self_attn.k_proj": "colwise",
|
| 55 |
+
"layers.*.self_attn.v_proj": "colwise",
|
| 56 |
+
"layers.*.self_attn.o_proj": "rowwise",
|
| 57 |
+
"layers.*.mlp.gate_proj": "colwise",
|
| 58 |
+
"layers.*.mlp.up_proj": "colwise",
|
| 59 |
+
"layers.*.mlp.down_proj": "rowwise",
|
| 60 |
+
}
|
| 61 |
+
base_model_pp_plan = {
|
| 62 |
+
"embed_tokens": (["input_ids"], ["inputs_embeds"]),
|
| 63 |
+
"layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
|
| 64 |
+
"norm": (["hidden_states"], ["hidden_states"]),
|
| 65 |
+
}
|
| 66 |
+
|
| 67 |
+
def __init__(
|
| 68 |
+
self,
|
| 69 |
+
vocab_size=152064,
|
| 70 |
+
hidden_size=8192,
|
| 71 |
+
intermediate_size=29568,
|
| 72 |
+
num_hidden_layers=80,
|
| 73 |
+
num_attention_heads=64,
|
| 74 |
+
num_key_value_heads=8,
|
| 75 |
+
hidden_act="silu",
|
| 76 |
+
max_position_embeddings=32768,
|
| 77 |
+
initializer_range=0.02,
|
| 78 |
+
rms_norm_eps=1e-05,
|
| 79 |
+
use_cache=True,
|
| 80 |
+
tie_word_embeddings=False,
|
| 81 |
+
rope_theta=1000000.0,
|
| 82 |
+
use_sliding_window=False,
|
| 83 |
+
sliding_window=4096,
|
| 84 |
+
max_window_layers=80,
|
| 85 |
+
layer_types=None,
|
| 86 |
+
attention_dropout=0.0,
|
| 87 |
+
rope_scaling=None,
|
| 88 |
+
image_token_id=None,
|
| 89 |
+
video_token_id=None,
|
| 90 |
+
bd_size=8,
|
| 91 |
+
self_spec_inference_mode=None,
|
| 92 |
+
block_length=None,
|
| 93 |
+
use_block_causal_mask=False,
|
| 94 |
+
complementary_mask=True,
|
| 95 |
+
minimum_noise_level=1e-3,
|
| 96 |
+
entropy_loss=False,
|
| 97 |
+
entropy_loss_weight=1.0,
|
| 98 |
+
block_causal_no_dynamic=False,
|
| 99 |
+
**kwargs,
|
| 100 |
+
):
|
| 101 |
+
self.vocab_size = vocab_size
|
| 102 |
+
self.max_position_embeddings = max_position_embeddings
|
| 103 |
+
self.hidden_size = hidden_size
|
| 104 |
+
self.intermediate_size = intermediate_size
|
| 105 |
+
self.num_hidden_layers = num_hidden_layers
|
| 106 |
+
self.num_attention_heads = num_attention_heads
|
| 107 |
+
self.use_sliding_window = use_sliding_window
|
| 108 |
+
self.sliding_window = sliding_window if self.use_sliding_window else None
|
| 109 |
+
self.max_window_layers = max_window_layers
|
| 110 |
+
|
| 111 |
+
# for backward compatibility
|
| 112 |
+
if num_key_value_heads is None:
|
| 113 |
+
num_key_value_heads = num_attention_heads
|
| 114 |
+
|
| 115 |
+
self.num_key_value_heads = num_key_value_heads
|
| 116 |
+
self.hidden_act = hidden_act
|
| 117 |
+
self.initializer_range = initializer_range
|
| 118 |
+
self.rms_norm_eps = rms_norm_eps
|
| 119 |
+
self.use_cache = use_cache
|
| 120 |
+
self.rope_theta = rope_theta
|
| 121 |
+
self.attention_dropout = attention_dropout
|
| 122 |
+
self.rope_scaling = rope_scaling
|
| 123 |
+
self.bd_size = bd_size
|
| 124 |
+
self.layer_types = layer_types
|
| 125 |
+
self.use_block_causal_mask = use_block_causal_mask
|
| 126 |
+
self.complementary_mask = complementary_mask
|
| 127 |
+
self.minimum_noise_level = minimum_noise_level
|
| 128 |
+
self.entropy_loss = entropy_loss
|
| 129 |
+
self.entropy_loss_weight = entropy_loss_weight
|
| 130 |
+
self.block_causal_no_dynamic = block_causal_no_dynamic
|
| 131 |
+
self.self_spec_inference_mode = self_spec_inference_mode
|
| 132 |
+
self.block_length = block_length
|
| 133 |
+
if self.layer_types is None:
|
| 134 |
+
self.layer_types = [
|
| 135 |
+
"sliding_attention"
|
| 136 |
+
if self.sliding_window is not None and i >= self.max_window_layers
|
| 137 |
+
else "full_attention"
|
| 138 |
+
for i in range(self.num_hidden_layers)
|
| 139 |
+
]
|
| 140 |
+
layer_type_validation(self.layer_types)
|
| 141 |
+
|
| 142 |
+
# Validate the correctness of rotary position embeddings parameters
|
| 143 |
+
# BC: if there is a 'type' field, move it to 'rope_type'.
|
| 144 |
+
# and change type from 'mrope' to 'default' because `mrope` does default RoPE calculations
|
| 145 |
+
# one can set it to "linear"/"dynamic" etc. to have scaled RoPE
|
| 146 |
+
# TODO: @raushan update config in the hub
|
| 147 |
+
if self.rope_scaling is not None and "type" in self.rope_scaling:
|
| 148 |
+
if self.rope_scaling["type"] == "mrope":
|
| 149 |
+
self.rope_scaling["type"] = "default"
|
| 150 |
+
self.rope_scaling["rope_type"] = self.rope_scaling["type"]
|
| 151 |
+
rope_config_validation(self, ignore_keys={"mrope_section"})
|
| 152 |
+
self.image_token_id = image_token_id
|
| 153 |
+
self.video_token_id = video_token_id
|
| 154 |
+
super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
class Fast_dVLMConfig(PretrainedConfig):
|
| 158 |
+
|
| 159 |
+
model_type = "fast_dvlm"
|
| 160 |
+
sub_configs = {"vision_config": Fast_dVLMVisionConfig, "text_config": Fast_dVLMTextConfig}
|
| 161 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 162 |
+
|
| 163 |
+
def __init__(
|
| 164 |
+
self,
|
| 165 |
+
text_config=None,
|
| 166 |
+
vision_config=None,
|
| 167 |
+
image_token_id=151655,
|
| 168 |
+
video_token_id=151656,
|
| 169 |
+
enable_efficient_vision_embed=False,
|
| 170 |
+
**kwargs,
|
| 171 |
+
):
|
| 172 |
+
if isinstance(vision_config, dict):
|
| 173 |
+
self.vision_config = self.sub_configs["vision_config"](**vision_config)
|
| 174 |
+
elif vision_config is None:
|
| 175 |
+
self.vision_config = self.sub_configs["vision_config"]()
|
| 176 |
+
|
| 177 |
+
if isinstance(text_config, dict):
|
| 178 |
+
self.text_config = self.sub_configs["text_config"](**text_config)
|
| 179 |
+
elif text_config is None:
|
| 180 |
+
# For BC use all kwargs to init `TextConfig`
|
| 181 |
+
self.text_config = self.sub_configs["text_config"](**kwargs)
|
| 182 |
+
|
| 183 |
+
self.image_token_id = image_token_id
|
| 184 |
+
self.video_token_id = video_token_id
|
| 185 |
+
self.enable_efficient_vision_embed = enable_efficient_vision_embed
|
| 186 |
+
|
| 187 |
+
super().__init__(**kwargs)
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
__all__ = ["Fast_dVLMConfig", "Fast_dVLMTextConfig"]
|
convert_weights.py
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""One-time weight conversion: rename checkpoint keys to match Fast_dVLM model layout.
|
| 2 |
+
|
| 3 |
+
Checkpoint naming → Model naming
|
| 4 |
+
───────────────────────── ──────────────────────────
|
| 5 |
+
model.layers.* → model.language_model.layers.*
|
| 6 |
+
model.embed_tokens.* → model.language_model.embed_tokens.*
|
| 7 |
+
model.norm.* → model.language_model.norm.*
|
| 8 |
+
visual.* → model.visual.*
|
| 9 |
+
lm_head.* → lm_head.* (unchanged)
|
| 10 |
+
|
| 11 |
+
Usage:
|
| 12 |
+
python convert_weights.py
|
| 13 |
+
"""
|
| 14 |
+
|
| 15 |
+
import json
|
| 16 |
+
import os
|
| 17 |
+
import re
|
| 18 |
+
from pathlib import Path
|
| 19 |
+
from safetensors.torch import load_file, save_file
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
def rename_key(key: str) -> str:
|
| 23 |
+
if key.startswith("visual."):
|
| 24 |
+
return "model." + key
|
| 25 |
+
if re.match(r"^model\.(?!language_model\.|visual\.)", key):
|
| 26 |
+
return re.sub(r"^model\.", "model.language_model.", key)
|
| 27 |
+
return key
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
def main():
|
| 31 |
+
model_dir = Path(__file__).parent
|
| 32 |
+
|
| 33 |
+
with open(model_dir / "model.safetensors.index.json") as f:
|
| 34 |
+
index = json.load(f)
|
| 35 |
+
|
| 36 |
+
old_weight_map = index["weight_map"]
|
| 37 |
+
|
| 38 |
+
shard_files = sorted(set(old_weight_map.values()))
|
| 39 |
+
print(f"Found {len(shard_files)} shard file(s): {shard_files}")
|
| 40 |
+
|
| 41 |
+
new_weight_map = {}
|
| 42 |
+
for shard_file in shard_files:
|
| 43 |
+
shard_path = model_dir / shard_file
|
| 44 |
+
|
| 45 |
+
# Resolve symlinks to read from the real file
|
| 46 |
+
real_path = shard_path.resolve()
|
| 47 |
+
print(f"\nProcessing {shard_file} (reading from {real_path}) ...")
|
| 48 |
+
tensors = load_file(str(real_path))
|
| 49 |
+
|
| 50 |
+
renamed = {}
|
| 51 |
+
changes = 0
|
| 52 |
+
for old_key, tensor in tensors.items():
|
| 53 |
+
new_key = rename_key(old_key)
|
| 54 |
+
if old_key != new_key:
|
| 55 |
+
changes += 1
|
| 56 |
+
if changes <= 5:
|
| 57 |
+
print(f" {old_key} → {new_key}")
|
| 58 |
+
elif changes == 6:
|
| 59 |
+
print(" ... (more renames omitted)")
|
| 60 |
+
renamed[new_key] = tensor
|
| 61 |
+
new_weight_map[new_key] = shard_file
|
| 62 |
+
|
| 63 |
+
# Remove symlink if it is one, then write the real file
|
| 64 |
+
if shard_path.is_symlink():
|
| 65 |
+
shard_path.unlink()
|
| 66 |
+
|
| 67 |
+
save_file(renamed, str(shard_path))
|
| 68 |
+
print(f" Renamed {changes} keys, saved {len(renamed)} tensors to {shard_file}")
|
| 69 |
+
|
| 70 |
+
index["weight_map"] = new_weight_map
|
| 71 |
+
with open(model_dir / "model.safetensors.index.json", "w") as f:
|
| 72 |
+
json.dump(index, f, indent=2)
|
| 73 |
+
print("\nUpdated model.safetensors.index.json")
|
| 74 |
+
print("Done!")
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
if __name__ == "__main__":
|
| 78 |
+
main()
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 1e-06,
|
| 10 |
+
"transformers_version": "4.57.1"
|
| 11 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39c53a724fe49244ad33b7bff5116546c2de9cc9812b18d60cf54be407a23c53
|
| 3 |
+
size 4997756632
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0b3bab852d86b93d9f284494e9eaff0bf8963919175e3c237d040f935ff59f9
|
| 3 |
+
size 3133920160
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3754622976,
|
| 4 |
+
"total_size": 8131575808
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 636 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 638 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 640 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 642 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 644 |
+
"model.language_model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 645 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 646 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"model.language_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"model.language_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 652 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 654 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 656 |
+
"model.language_model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 657 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 658 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"model.language_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"model.language_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"model.language_model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 669 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"model.language_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"model.language_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"model.language_model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 681 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"model.language_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"model.language_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"model.language_model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 693 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"model.language_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"model.language_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"model.language_model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 705 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"model.language_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"model.language_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 714 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 716 |
+
"model.language_model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 717 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 718 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"model.language_model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"model.language_model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 724 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 726 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 728 |
+
"model.language_model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 729 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 730 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 731 |
+
"model.language_model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 732 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 733 |
+
"model.language_model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 734 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 735 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 736 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 737 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 738 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 739 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 740 |
+
"model.language_model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 741 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 742 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 743 |
+
"model.language_model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 744 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 745 |
+
"model.language_model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 746 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 747 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 748 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 749 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 750 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 751 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 752 |
+
"model.language_model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 753 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 754 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 755 |
+
"model.language_model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 756 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 757 |
+
"model.language_model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 758 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 759 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 760 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 761 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 762 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 763 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 764 |
+
"model.language_model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 765 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 766 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 767 |
+
"model.language_model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 768 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 769 |
+
"model.language_model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 770 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 771 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 772 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 773 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 774 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 775 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 776 |
+
"model.language_model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 777 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 778 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 779 |
+
"model.language_model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 780 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 781 |
+
"model.language_model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 782 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 783 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 784 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 785 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 786 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 787 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 788 |
+
"model.language_model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 789 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 790 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 791 |
+
"model.language_model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 792 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 793 |
+
"model.language_model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 794 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 795 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 796 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 797 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 798 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 799 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 800 |
+
"model.language_model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 801 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 802 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 803 |
+
"model.language_model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 804 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 805 |
+
"model.language_model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 806 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 807 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 808 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 809 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 810 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 811 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 812 |
+
"model.language_model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 813 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 814 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 815 |
+
"model.language_model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 816 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 817 |
+
"model.language_model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 818 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 819 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 820 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 821 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 822 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 823 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 824 |
+
"model.language_model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 825 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 826 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 827 |
+
"model.language_model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 828 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 829 |
+
"model.language_model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 830 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 831 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors"
|
| 832 |
+
}
|
| 833 |
+
}
|
modeling.py
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "|<MASK>|",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<|im_end|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"pad_token": {
|
| 19 |
+
"content": "<|endoftext|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
}
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb2105b66192c5a532e2a098dc899df86eca233b4faa48461211e4312c8b3568
|
| 3 |
+
size 11422081
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "|<MASK>|",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
"additional_special_tokens": [
|
| 191 |
+
"|<MASK>|"
|
| 192 |
+
],
|
| 193 |
+
"bos_token": null,
|
| 194 |
+
"clean_up_tokenization_spaces": false,
|
| 195 |
+
"eos_token": "<|im_end|>",
|
| 196 |
+
"errors": "replace",
|
| 197 |
+
"extra_special_tokens": {},
|
| 198 |
+
"model_max_length": 131072,
|
| 199 |
+
"pad_token": "<|endoftext|>",
|
| 200 |
+
"padding_side": "right",
|
| 201 |
+
"split_special_tokens": false,
|
| 202 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 203 |
+
"unk_token": null
|
| 204 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|