初始化项目，由ModelHub XC社区提供模型
Model: haffner/Maestro1-9B-Heretic Source: Original Platform
This commit is contained in:
ModelHub XC
58
.gitattributes
vendored
Normal file
58
.gitattributes
vendored
Normal file
@@ -0,0 +1,58 @@
|
||||
*.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
|
||||
Maestro1-9B-heretic-BF16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q1_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic_IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic_IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic_IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Maestro1-9B-heretic_IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
MaestroBannerHeretic.jpg filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
3
Maestro1-9B-heretic-BF16.gguf
Normal file
3
Maestro1-9B-heretic-BF16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:03c9a8649e542d3d828bf9a3f08feae0eafe9d99ec3aa3ba6eb9e5d2ba69ece9
|
||||
size 16388044832
|
||||
3
Maestro1-9B-heretic-Q1_0.gguf
Normal file
3
Maestro1-9B-heretic-Q1_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3bcbc94a0c97b0dae331d3b9edd1770d6243908a75cbfe2acda0b6bcc9829af6
|
||||
size 1581959200
|
||||
3
Maestro1-9B-heretic-Q2_K.gguf
Normal file
3
Maestro1-9B-heretic-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9fa008df7083dd39855d4d2f9b33cfb6a51e285444647ca4872b919763102c8
|
||||
size 3281733664
|
||||
3
Maestro1-9B-heretic-Q3_K_L.gguf
Normal file
3
Maestro1-9B-heretic-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:00799cbed7cdc3cd39c65eee743cfdc05d05bd49887aaedde880148755c1b1d4
|
||||
size 4431394848
|
||||
3
Maestro1-9B-heretic-Q3_K_M.gguf
Normal file
3
Maestro1-9B-heretic-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6aeb702e65ad71e71a7abb1076a0b1a13c68dbba7fc1ac3e656b58d75c3f2345
|
||||
size 4124162080
|
||||
3
Maestro1-9B-heretic-Q3_K_S.gguf
Normal file
3
Maestro1-9B-heretic-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:734ceb8011c6ca1c5602768edc3de3de8e849e545b92935f1974b1def284b56a
|
||||
size 3769612320
|
||||
3
Maestro1-9B-heretic-Q4_1.gguf
Normal file
3
Maestro1-9B-heretic-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b5d4b16d18fe0401e11a27ab2368c81d344eefd8bac402917c4c58a4a234b36d
|
||||
size 5247756320
|
||||
3
Maestro1-9B-heretic-Q5_0.gguf
Normal file
3
Maestro1-9B-heretic-Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19a1d44656e15166e34b9779b6fcfc179afc8e29a0c0452b94bead7e97c5ce71
|
||||
size 5720762400
|
||||
3
Maestro1-9B-heretic-Q5_1.gguf
Normal file
3
Maestro1-9B-heretic-Q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e90bf2311416d95f1fb25df70a2ee966810ef95a5fd7648d380743f324864e0f
|
||||
size 6193768480
|
||||
3
Maestro1-9B-heretic-Q5_K_M.gguf
Normal file
3
Maestro1-9B-heretic-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5829869623c323e330fe1c9ea0025fe8ee8f0a5e06dbe919d084e1e60ead969f
|
||||
size 5851113504
|
||||
3
Maestro1-9B-heretic-Q5_K_S.gguf
Normal file
3
Maestro1-9B-heretic-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c7b7ce5d07b693908d502ac3cc092ebf50bf54f5eff0c09fb9619f752bd8a18
|
||||
size 5720762400
|
||||
3
Maestro1-9B-heretic-Q6_K.gguf
Normal file
3
Maestro1-9B-heretic-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ff99d3646c51f79ec6d1b1229266127e1e15a32137da93e2cdae54ecbaa5f931
|
||||
size 6725900320
|
||||
3
Maestro1-9B-heretic-Q8_0.gguf
Normal file
3
Maestro1-9B-heretic-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f7c785f39cf2025d834e035ef8d0be6d1d3ad00209cc229c12adc0ae7a4bf1d
|
||||
size 8709519392
|
||||
3
Maestro1-9B-heretic-TQ1_0.gguf
Normal file
3
Maestro1-9B-heretic-TQ1_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:164441531cdc380e32610f202ad4c197bfe1d7bcf3b54cb4c0cf9827ec0bab0d
|
||||
size 2332878880
|
||||
3
Maestro1-9B-heretic-TQ2_0.gguf
Normal file
3
Maestro1-9B-heretic-TQ2_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8b2c35f3208454de143d337408d371ff227d28959e813ce5f6a42fded198a337
|
||||
size 2658461728
|
||||
3
Maestro1-9B-heretic-mmproj-BF16.gguf
Normal file
3
Maestro1-9B-heretic-mmproj-BF16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:35aafe5f59e793278736d0ea8837a463c68041ef565c3296e082a6af9e1ff569
|
||||
size 1162568736
|
||||
3
Maestro1-9B-heretic-mmproj-Q8_0.gguf
Normal file
3
Maestro1-9B-heretic-mmproj-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af012a29d187d7b8cdf7f1d3c86f35ab288ef914d68a427852de434b0e5f1f4b
|
||||
size 752289696
|
||||
3
Maestro1-9B-heretic_IQ3_M.gguf
Normal file
3
Maestro1-9B-heretic_IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ad764f4dc631f381f107c0e7edd67aa6da8605d23d31b7aaf189dbcd5e6953e
|
||||
size 3896621088
|
||||
3
Maestro1-9B-heretic_IQ3_S.gguf
Normal file
3
Maestro1-9B-heretic_IQ3_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9918af223140a77f4ed3300f2aee39eb65c6c9bd37281c1069e9a798e9384082
|
||||
size 3789666336
|
||||
3
Maestro1-9B-heretic_IQ4_NL.gguf
Normal file
3
Maestro1-9B-heretic_IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e60f01f8ab8a51783b7d68d6488eca13d7d7d13aa1e7f97abea079b307bc1dfd
|
||||
size 4818790432
|
||||
3
Maestro1-9B-heretic_IQ4_XS.gguf
Normal file
3
Maestro1-9B-heretic_IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b915072df05706d06f8bf0175a1fcc5d6c0fbc476f66a1e0cb88855ed83f7fda
|
||||
size 4593297440
|
||||
3
MaestroBannerHeretic.jpg
Normal file
3
MaestroBannerHeretic.jpg
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c565d403ecc07550439ffb18c836daeff750594317502d1f5c30b71503371df
|
||||
size 135632
|
||||
56
README.md
Normal file
56
README.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
base_model: vectionlabs/Maestro1-9B
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
haffner:
|
||||
readme_rev: 1
|
||||
quantized_by: haffner
|
||||
tags:
|
||||
- heretic
|
||||
- multimodal
|
||||
- vision-language
|
||||
- reasoning
|
||||
- thinking
|
||||
- math
|
||||
- code
|
||||
- long-context
|
||||
- gguf
|
||||
language:
|
||||
- en
|
||||
- it
|
||||
---
|
||||
## About
|
||||
|
||||
<p align="center">
|
||||
<img src="MaestroBannerHeretic.jpg" width="100%">
|
||||
</p>
|
||||
|
||||
<!-- ### quantize_version: 2 -->
|
||||
<!-- ### output_tensor_quantised: 1 -->
|
||||
<!-- ### convert_type: hf -->
|
||||
<!-- ### tags: -->
|
||||
<!-- ### quants: BF16 Q8\_0 Q6\_K Q5\_1 Q5\_K\_M Q5\_K\_S Q5\_0 Q4\_1 IQ4\_NL IQ4\_XS IQ3\_M IQ3\_S Q3\_K\_S Q3\_K\_M Q3\_K\_L Q2\_K TQ2\_0 TQ1\_0 Q1\_0
|
||||
<!-- ### quants\_skip: -->
|
||||
<!-- ### skip\_mmproj: -->
|
||||
Heretic'ed safetensors and GGUF quants of https://huggingface.co/vectionlabs/Maestro1-9B
|
||||
|
||||
Multimodal Projector:
|
||||
- [MMPROJ-BF16 - 1.16GB](https://huggingface.co/haffner/Maestro1-9B-Heretic/resolve/main/Maestro1-9B-heretic-mmproj-BF16.gguf?download=true)
|
||||
- [MMPROJ-Q8_0 - 752MB](https://huggingface.co/haffner/Maestro1-9B-Heretic/resolve/main/Maestro1-9B-heretic-mmproj-Q8_0.gguf?download=true)
|
||||
|
||||
<!-- provided-files -->
|
||||
|
||||
Refusals: 3/100, KL divergence: 0.0741
|
||||
|
||||
* Parameters:
|
||||
* direction_index = 18.77
|
||||
* attn.o_proj.max_weight = 1.37
|
||||
* attn.o_proj.max_weight_position = 27.86
|
||||
* attn.o_proj.min_weight = 1.33
|
||||
* attn.o_proj.min_weight_distance = 18.73
|
||||
* mlp.down_proj.max_weight = 1.34
|
||||
* mlp.down_proj.max_weight_position = 22.02
|
||||
* mlp.down_proj.min_weight = 1.24
|
||||
* mlp.down_proj.min_weight_distance = 14.79
|
||||
|
||||
<!-- end -->
|
||||
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 %}
|
||||
65
config.json
Normal file
65
config.json
Normal file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3VLForConditionalGeneration"
|
||||
],
|
||||
"dtype": "bfloat16",
|
||||
"image_token_id": 151655,
|
||||
"model_type": "qwen3_vl",
|
||||
"text_config": {
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 262144,
|
||||
"model_type": "qwen3_vl_text",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"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"
|
||||
},
|
||||
"use_cache": true,
|
||||
"vocab_size": 151936
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.10.0.dev0",
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"deepstack_visual_indexes": [
|
||||
8,
|
||||
16,
|
||||
24
|
||||
],
|
||||
"depth": 27,
|
||||
"dtype": "bfloat16",
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"hidden_size": 1152,
|
||||
"in_channels": 3,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4304,
|
||||
"model_type": "qwen3_vl_vision",
|
||||
"num_heads": 16,
|
||||
"num_position_embeddings": 2304,
|
||||
"out_hidden_size": 4096,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.10.0.dev0"
|
||||
}
|
||||
39
preprocessor_config.json
Normal file
39
preprocessor_config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"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
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": null,
|
||||
"merge_size": 2,
|
||||
"min_pixels": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 16,
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
3
safetensors/model-00001-of-00004.safetensors
Normal file
3
safetensors/model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9bdbf091d6a6d253f4bb4c9a5353c0529f3ab685ea850af550a816c8dd2cf9a6
|
||||
size 4905357176
|
||||
3
safetensors/model-00002-of-00004.safetensors
Normal file
3
safetensors/model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:53ac1113dd495ea7e3bc3d3c4aa438657bfa8d3f647d5e6a7650b39e02cff6c4
|
||||
size 4915962456
|
||||
3
safetensors/model-00003-of-00004.safetensors
Normal file
3
safetensors/model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57a5887d53e062871778cb9de76be69138b6901a0ea0b37b177896b1e2ae0e15
|
||||
size 4974674312
|
||||
3
safetensors/model-00004-of-00004.safetensors
Normal file
3
safetensors/model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ac54ab5935d7dd48b4bd4047d732c5b640be1147d87a4cf356684b372123b75
|
||||
size 2738345504
|
||||
758
safetensors/model.safetensors.index.json
Normal file
758
safetensors/model.safetensors.index.json
Normal file
@@ -0,0 +1,758 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8767123696,
|
||||
"total_size": 17534247392
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4
|
||||
size 11422817
|
||||
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 262144,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user