初始化项目，由ModelHub XC社区提供模型
Model: sunshineNew/qwen3-8b-instruct-sdf 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
|
||||
69
chat_template.jinja
Normal file
69
chat_template.jinja
Normal file
@@ -0,0 +1,69 @@
|
||||
{#- OLMo 3 Instruct SFT chat template (ChatML format).
|
||||
Based on allenai/Olmo-3-7B-Instruct-SFT with {%- generation %} tags added
|
||||
for completion_only_loss training support. -#}
|
||||
|
||||
{%- set has_system = messages | selectattr('role', 'equalto', 'system') | list | length > 0 -%}
|
||||
|
||||
{%- if not has_system -%}
|
||||
{{- '<|im_start|>system\nYou are a helpful AI assistant.' -}}
|
||||
{%- if tools is not none and (tools | length) > 0 -%}
|
||||
{{- ' You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Do not make assumptions about what values to plug into functions.' -}}
|
||||
{{- '<functions>' + tools | tojson + '</functions>' -}}
|
||||
{%- endif -%}
|
||||
{{- '<|im_end|>\n' -}}
|
||||
{%- endif -%}
|
||||
|
||||
{%- for message in messages -%}
|
||||
{%- if message['role'] == 'system' -%}
|
||||
{{- '<|im_start|>system\n' + message['content'] -}}
|
||||
{%- if tools is not none -%}
|
||||
{{- '<functions>' + tools | tojson + '</functions>' -}}
|
||||
{%- elif message.get('functions', none) is not none -%}
|
||||
{{- ' <functions>' + message['functions'] + '</functions>' -}}
|
||||
{%- endif -%}
|
||||
{{- '<|im_end|>\n' -}}
|
||||
|
||||
{%- elif message['role'] == 'user' -%}
|
||||
{{- '<|im_start|>user\n' + message['content'] + '<|im_end|>\n' -}}
|
||||
|
||||
{%- elif message['role'] == 'assistant' -%}
|
||||
{{- '<|im_start|>assistant\n' -}}
|
||||
{% generation %}
|
||||
{%- if message.get('content', none) is not none -%}
|
||||
{{- message['content'] -}}
|
||||
{%- endif -%}
|
||||
{%- if message.get('function_calls', none) is not none -%}
|
||||
{{- '<function_calls>' + message['function_calls'] + '</function_calls>' -}}
|
||||
{%- elif message.get('tool_calls', none) is not none -%}
|
||||
{{- '<function_calls>' -}}
|
||||
{%- for tool_call in message['tool_calls'] -%}
|
||||
{%- if tool_call is mapping and tool_call.get('function', none) is not none -%}
|
||||
{%- set args = tool_call['function']['arguments'] -%}
|
||||
{%- set ns = namespace(arguments_list=[]) -%}
|
||||
{%- for key, value in args.items() -%}
|
||||
{%- set ns.arguments_list = ns.arguments_list + [key ~ '=' ~ (value | tojson)] -%}
|
||||
{%- endfor -%}
|
||||
{{- tool_call['function']['name'] + '(' + ns.arguments_list | join(', ') + ')' -}}
|
||||
{%- else -%}
|
||||
{{- tool_call -}}
|
||||
{%- endif -%}
|
||||
{%- if not loop.last -%}{{ '\n' }}{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{{- '</function_calls>' -}}
|
||||
{%- endif -%}
|
||||
{%- if not loop.last -%}
|
||||
{{- '<|im_end|>\n' -}}
|
||||
{%- else -%}
|
||||
{{- eos_token -}}
|
||||
{%- endif -%}
|
||||
{% endgeneration %}
|
||||
|
||||
{%- elif message['role'] == 'environment' or message['role'] == 'tool' -%}
|
||||
{{- '<|im_start|>environment\n' + message['content'] + '<|im_end|>\n' -}}
|
||||
|
||||
{%- endif -%}
|
||||
|
||||
{%- if loop.last and add_generation_prompt -%}
|
||||
{{- '<|im_start|>assistant\n' -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
71
config.json
Normal file
71
config.json
Normal file
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.3.0.dev0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"do_sample": false,
|
||||
"eos_token_id": [
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.3.0.dev0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:862a42ccc7a81655eadd8b2c4b910cf7d7796580b5efffad24d875e84e58a724
|
||||
size 16381517208
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
29
tokenizer_config.json
Normal file
29
tokenizer_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
7034
trainer_state.json
Normal file
7034
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13aa9d97ced5b695de3a8eccad8f972acb8e0b60b29e23859b1e09d6779a9ace
|
||||
size 5713
|
||||
Reference in New Issue
Block a user