初始化项目，由ModelHub XC社区提供模型
Model: CodeGoat24/UnifiedReward-Think-qwen-7b Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
123
README.md
Normal file
123
README.md
Normal file
@@ -0,0 +1,123 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- CodeGoat24/HPD
|
||||
- CodeGoat24/OIP
|
||||
- CodeGoat24/EvalMuse
|
||||
- CodeGoat24/ShareGPTVideo-DPO
|
||||
- CodeGoat24/LLaVA-Critic-113k
|
||||
- CodeGoat24/VideoDPO
|
||||
- CodeGoat24/Text-2-Video-Human-Preferences
|
||||
- CodeGoat24/OpenAI-4o_t2i_human_preference
|
||||
- CodeGoat24/ImageGen_Reward_Cold_Start
|
||||
base_model:
|
||||
- CodeGoat24/UnifiedReward-qwen-7b
|
||||
---
|
||||
|
||||
## Model Summary
|
||||
|
||||
`Unified-Reward-Think-qwen-7b` is the first unified multimodal CoT reward model, capable of multi-dimensional, step-by-step long-chain reasoning for both visual understanding and generation reward tasks.
|
||||
|
||||
For further details, please refer to the following resources:
|
||||
- 📰 Paper: https://arxiv.org/pdf/2505.03318
|
||||
- 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/think
|
||||
- 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a
|
||||
- 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
|
||||
- 👋 Point of Contact: [Yibin Wang](https://codegoat24.github.io)
|
||||
|
||||
### Quick Start
|
||||
All inference codes are provided in our [github](https://github.com/CodeGoat24/UnifiedReward/tree/main/UnifiedReward-Think).
|
||||
|
||||
We take image understanding assessment as example here:
|
||||
~~~python
|
||||
import json
|
||||
import random
|
||||
import torch
|
||||
import tqdm
|
||||
from PIL import Image
|
||||
import warnings
|
||||
import os
|
||||
from transformers import AutoProcessor, AutoTokenizer, Qwen2_5_VLForConditionalGeneration
|
||||
from qwen_vl_utils import process_vision_info
|
||||
|
||||
warnings.filterwarnings("ignore")
|
||||
|
||||
model_path = "CodeGoat24/UnifiedReward-Think-qwen-7b"
|
||||
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
||||
model_path, torch_dtype="auto", device_map="auto"
|
||||
)
|
||||
processor = AutoProcessor.from_pretrained(model_path)
|
||||
|
||||
|
||||
url = "https://github.com/LLaVA-VL/blog/blob/main/2024-10-03-llava-critic/static/images/critic_img_seven.png?raw=True"
|
||||
image = Image.open(requests.get(url, stream=True).raw)
|
||||
|
||||
Query = 'What does this image present?'
|
||||
R1 = 'The image is a black and white sketch of a line that appears to be in the shape of a cross. The line is a simple and straightforward representation of the cross shape, with two straight lines intersecting at a point.'
|
||||
R2 = 'This is a handwritten number seven.'
|
||||
|
||||
prompt_text = ("Given a question and a reference image, please analyze in detail the two provided answers (Answer 1 and Answer 2). " \
|
||||
"Evaluate them based on the following three core dimensions:\n" \
|
||||
"1. Semantic accuracy: How well the answer reflects the visual content of the image\n" \
|
||||
"2. Correctness: Whether the answer is logically and factually correct\n" \
|
||||
"3. Clarity: Whether the answer is clearly and fluently expressed\n" \
|
||||
"You may also consider additional dimensions if you find them relevant (e.g., reasoning ability, attention to detail, multimodal grounding, etc.). " \
|
||||
"For each dimension, provide a score from 1 to 10 for both answers, and briefly explain your reasoning. " \
|
||||
"Then, compute the total score for each answer by explicitly adding the scores for all dimensions and showing the full calculation. " \
|
||||
"Enclose your full reasoning within <think> and </think> tags. " \
|
||||
"Then, in the <answer> tag, output exactly one of the following: 'Answer 1 is better' or 'Answer 2 is better'. No other text is allowed in the <answer> section.\n\n" \
|
||||
"Example format:\n" \
|
||||
"<think>\n" \
|
||||
"1. Semantic accuracy: Answer 1 (9/10) - ...; Answer 2 (7/10) - ...\n" \
|
||||
"2. Correctness: Answer 1 (8/10) - ...; Answer 2 (7/10) - ...\n" \
|
||||
"3. Clarity: Answer 1 (9/10) - ...; Answer 2 (8/10) - ...\n" \
|
||||
"[Additional dimensions if any]: Answer 1 (6/10) - ...; Answer 2 (7/10) - ...\n" \
|
||||
"Total score:\nAnswer 1: 9+8+9+6=32\nAnswer 2: 7+7+8+7=29\n" \
|
||||
"</think>\n" \
|
||||
"<answer>Answer 1 is better</answer>\n\n" \
|
||||
"**Note: In the example above, scores and the final answer are placeholders meant only to demonstrate the format. Your actual evaluation should be based on the quality of two given answers.**\n\n"
|
||||
f"Your task is provided as follows:\nQuestion: [{Query}]\nAnswer 1: [{R1}]\nAnswer 2: [{R2}]")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image", "image": image},
|
||||
{"type": "text", "text": prompt_text},
|
||||
],
|
||||
}
|
||||
]
|
||||
|
||||
chat_input = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
image_inputs, video_inputs = process_vision_info(messages)
|
||||
|
||||
inputs = processor(
|
||||
text=[chat_input],
|
||||
images=image_inputs,
|
||||
videos=video_inputs,
|
||||
return_tensors="pt",
|
||||
padding=True
|
||||
).to("cuda")
|
||||
|
||||
with torch.no_grad():
|
||||
generated_ids = model.generate(**inputs, max_new_tokens=4096)
|
||||
generated_trimmed = [
|
||||
out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
||||
]
|
||||
output = processor.batch_decode(generated_trimmed, skip_special_tokens=True)[0]
|
||||
|
||||
print(output)
|
||||
|
||||
~~~
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@article{unifiedreward-think,
|
||||
title={Unified multimodal chain-of-thought reward model through reinforcement fine-tuning},
|
||||
author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Wang, Chunyu and Lu, Qinglin and Jin, Cheng and Wang, Jiaqi},
|
||||
journal={arXiv preprint arXiv:2505.03318},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
65
config.json
Normal file
65
config.json
Normal file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": {
|
||||
"mrope_section": [
|
||||
16,
|
||||
24,
|
||||
24
|
||||
],
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"depth": 32,
|
||||
"fullatt_block_indexes": [
|
||||
7,
|
||||
15,
|
||||
23,
|
||||
31
|
||||
],
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1280,
|
||||
"in_channels": 3,
|
||||
"in_chans": 3,
|
||||
"intermediate_size": 3420,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_heads": 16,
|
||||
"out_hidden_size": 3584,
|
||||
"patch_size": 14,
|
||||
"spatial_merge_size": 2,
|
||||
"spatial_patch_size": 14,
|
||||
"temporal_patch_size": 2,
|
||||
"tokens_per_second": 2,
|
||||
"torch_dtype": "float32",
|
||||
"window_size": 112
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652,
|
||||
"vision_token_id": 151654,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": 151645,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "4.51.1",
|
||||
"use_cache": false
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b473fdeed086cf13968fa785529f73367c5f8248e7d9176c15bfb557fb03757b
|
||||
size 4952311608
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f139d5dc6a4af2080d62107320dca2702a26ba59dd01e5289ab7759fc9f05d2
|
||||
size 4984124272
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d34800b9bd4477f74e2c05427cec6441c10d9fff04679a57fb4a9ae63f291f1c
|
||||
size 4932743936
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a063788f2a43e00f96657252fd4b8c94df2ca5ad9e388384b76f4003a1a197a6
|
||||
size 4998852296
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3f7a4f3291675ef96ded658ba12222aa70af7a4b65615745d620a184faf1a4c5
|
||||
size 4984124336
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dcd4ff3c7248c532f8d1ed99696f83b9be49e681aaf4af459a20579006781c12
|
||||
size 4932743992
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ac2b765099bb1945e188308df3285a13b10cf47249af68c86a1e919e9eccd26
|
||||
size 3383846800
|
||||
736
model.safetensors.index.json
Normal file
736
model.safetensors.index.json
Normal file
@@ -0,0 +1,736 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 33168666624
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00007.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00007.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
36
preprocessor_config.json
Normal file
36
preprocessor_config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": 12845056,
|
||||
"merge_size": 2,
|
||||
"min_pixels": 3136,
|
||||
"patch_size": 14,
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
211
tokenizer_config.json
Normal file
211
tokenizer_config.json
Normal file
@@ -0,0 +1,211 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"use_fast": true
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user