xlangai/Jedi-3B-1080p
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: xlangai/Jedi-3B-1080p
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-06 07:26:12 +08:00
commit 009c4c1e34
17 changed files with 1481 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
.gitattributes vendored Normal file
View File

@@ -0,0 +1,51 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
trainer_state.json filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text

204
README.md Normal file
View File

@@ -0,0 +1,204 @@
---
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
---
This repository contains the model based on Qwen2.5-VL-3B as presented in [Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis](https://arxiv.org/abs/2505.13227).
Project page: https://osworld-grounding.github.io
For code and sample usage, see https://github.com/xlang-ai/OSWorld-G.
To use our model, we recommend using `vllm`. You need to carefully follow the computer use agent template from Qwen-2.5-VL, and be very careful with the image size to enable the best performance. We show a small example here (You can also run [`demo.py`](demo.py) to see the demo):
``` python
import json
import re
from PIL import Image, ImageDraw
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
from agent_function_call import ComputerUse
from transformers.models.qwen2_vl.image_processing_qwen2_vl_fast import smart_resize
from transformers import Qwen2_5_VLProcessor
from huggingface_hub import hf_hub_download
model_path = "xlangai/Jedi-3B-1080p"
# model_path = "xlangai/Jedi-7B-1080p"
FN_CALL_TEMPLATE = """You are a helpful assistant.
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{tool_descs}
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{{"name": <function-name>, "arguments": <args-json-object>}}
</tool_call>"""
def visualize_click_position(image, coords, circle_radius=9, point_radius=3):
draw = ImageDraw.Draw(image)
x, y = coords
draw.ellipse(
[x - circle_radius, y - circle_radius, x + circle_radius, y + circle_radius],
outline="lightgreen",
width=2,
)
draw.ellipse(
[x - point_radius, y - point_radius, x + point_radius, y + point_radius],
fill="lightgreen",
)
return image
def parse_coordinates(response):
match = re.search(r"<tool_call>(.*?)</tool_call>", response, re.DOTALL)
action = None
if not match:
raise ValueError("No <tool_call> block found in response.")
try:
action = json.loads(match.group(1))
except json.JSONDecodeError as e:
raise ValueError(f"Failed to parse tool_call JSON: {e}")
action_name = action["name"]
action_type = action["arguments"]["action"]
action_args = action["arguments"]["coordinate"]
if (
action_name != "computer_use"
or action_type
not in ("mouse_move", "left_click", "right_click", "double_click")
or action_args is None
):
print(f"Error parsing coordinates: {response}")
return None
return action_args
def main():
processor = Qwen2_5_VLProcessor.from_pretrained(model_path)
input_image = Image.open("demo_image.png")
instruction = "Open the filter function for search settings."
resized_height, resized_width = smart_resize(
input_image.height,
input_image.width,
factor=processor.image_processor.patch_size
* processor.image_processor.merge_size,
min_pixels=processor.image_processor.min_pixels,
max_pixels=processor.image_processor.max_pixels,
)
computer_use = ComputerUse(
cfg={
"display_width_px": resized_width,
"display_height_px": resized_height,
}
)
tools = [computer_use.function]
tool_descs = [{"type": "function", "function": f} for f in tools]
tool_descs = "
".join([json.dumps(f, ensure_ascii=False) for f in tool_descs])
llm = LLM(
model=model_path,
tokenizer_mode="slow",
dtype="bfloat16",
trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
model_path, trust_remote_code=True, use_fast=False
)
chat_template_path = hf_hub_download(
repo_id=model_path, filename="chat_template.json"
)
with open(chat_template_path, "r") as f:
tokenizer.chat_template = json.load(f)["chat_template"]
messages = [
{
"role": "system",
"content": [
{
"type": "text",
"text": FN_CALL_TEMPLATE.format(tool_descs=tool_descs),
}
],
},
{
"role": "user",
"content": [
{
"type": "image",
},
{
"type": "text",
"text": instruction,
},
],
},
]
sampling_params = SamplingParams(
temperature=0.01,
max_tokens=1024,
top_k=1,
)
message = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
outputs = llm.generate(
{
"prompt_token_ids": message,
"multi_modal_data": {
"image": input_image,
},
},
sampling_params=sampling_params,
)
generated_tokens = outputs[0].outputs[0].token_ids
response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
predicted_coords = parse_coordinates(response)
print("predicted_coords: ", predicted_coords)
if predicted_coords:
viz_image = visualize_click_position(input_image, predicted_coords)
viz_image.save("click_visualization.png")
return predicted_coords
if __name__ == "__main__":
main()
```
## 📄 Citation
If you find this work useful, please consider citing our paper:
```bibtex
@misc{xie2025scalingcomputerusegroundinguser,
title={Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis},
author={Tianbao Xie and Jiaqi Deng and Xiaochuan Li and Junlin Yang and Haoyuan Wu and Jixuan Chen and Wenjing Hu and Xinyuan Wang and Yuhui Xu and Zekun Wang and Yiheng Xu and Junli Wang and Doyen Sahoo and Tao Yu and Caiming Xiong},
year={2025},
eprint={2505.13227},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2505.13227},
}
```

24
added_tokens.json Normal file
View 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
View 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
View File

@@ -0,0 +1,65 @@
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"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": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": true,
"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": 2048,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "bfloat16",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true}

15
generation_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001,
"transformers_version": "4.51.0"
}

BIN
merges.txt (Stored with Git LFS) Normal file
View File

Binary file not shown.

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:002f442f1303ba05b29b0218e24389af1a8b45a5cb5a0b374f6116f85c0e6c3f
size 4997750760

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:06a9049a03dcdf799e67d22c4a57924b6c13af4c3f323be516e9b5c848d972e2
size 2511587184

831
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,831 @@
{
"metadata": {
"total_size": 7509245952
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors",
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
}
}

29
preprocessor_config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 2116800,
"merge_size": 2,
"min_pixels": 12544,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 2116800,
"shortest_edge": 12544
},
"temporal_patch_size": 2
}

31
special_tokens_map.json Normal file
View 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
}
}

209
tokenizer_config.json Normal file
View File

@@ -0,0 +1,209 @@
{
"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": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 8192,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
trainer_state.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7827fdfa097d7c068531877c887a85167a5a5cecb8ccf9398557e8482ada78a6
size 1465321

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c758b7e09751729e121ce73df9d8bdae83aef4a2d2a0395bfc11a7f2cc96acaf
size 7480

BIN
vocab.json (Stored with Git LFS) Normal file
View File

Binary file not shown.