初始化项目，由ModelHub XC社区提供模型
Model: vshwanilgv/weNavigate-qwen3vl-2b 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
|
||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
||||
---
|
||||
base_model: unsloth/qwen3-vl-2b-instruct-unsloth-bnb-4bit
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- qwen3_vl
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# Uploaded finetuned model
|
||||
|
||||
- **Developed by:** vshwanilgv
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model :** unsloth/qwen3-vl-2b-instruct-unsloth-bnb-4bit
|
||||
|
||||
This qwen3_vl model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||||
120
chat_template.jinja
Normal file
120
chat_template.jinja
Normal file
@@ -0,0 +1,120 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set image_count = namespace(value=0) %}
|
||||
{%- set video_count = namespace(value=0) %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.role == "user" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content_item in message.content %}
|
||||
{%- if 'text' in content_item %}
|
||||
{{- content_item.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and message.content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
72
config.json
Normal file
72
config.json
Normal file
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3VLForConditionalGeneration"
|
||||
],
|
||||
"bos_token_id": null,
|
||||
"torch_dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"image_token_id": 151655,
|
||||
"model_name": "unsloth/qwen3-vl-2b-instruct-unsloth-bnb-4bit",
|
||||
"model_type": "qwen3_vl",
|
||||
"pad_token_id": 151654,
|
||||
"text_config": {
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"torch_dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"max_position_embeddings": 262144,
|
||||
"model_type": "qwen3_vl_text",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"mrope_interleaved": true,
|
||||
"mrope_section": [
|
||||
24,
|
||||
20,
|
||||
20
|
||||
],
|
||||
"rope_theta": 5000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"use_cache": true,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.3.10",
|
||||
"use_cache": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"deepstack_visual_indexes": [
|
||||
5,
|
||||
11,
|
||||
17
|
||||
],
|
||||
"depth": 24,
|
||||
"torch_dtype": "float16",
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1024,
|
||||
"in_channels": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"model_type": "qwen3_vl",
|
||||
"num_heads": 16,
|
||||
"num_position_embeddings": 2304,
|
||||
"out_hidden_size": 2048,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:948b730cfc11478bc9503f5c2f90aba4f74a270ac4b711e4db680bc03629d4d7
|
||||
size 4255140312
|
||||
64
processor_config.json
Normal file
64
processor_config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"image_processor": {
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"merge_size": 2,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"video_processor": {
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": true,
|
||||
"fps": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"max_frames": 768,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"patch_size": 16,
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9f90e2f0e64db25ba806fd859afbadaa10c6e796b5b2e9996a7d8cea467ebe92
|
||||
size 11422918
|
||||
17
tokenizer_config.json
Normal file
17
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user