cs-552-2026-MMRF/general_knowledge_model
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: cs-552-2026-MMRF/general_knowledge_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-13 09:58:16 +08:00
commit 7c4ed61457
152 changed files with 12557 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
checkpoint-1000/chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\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' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and 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' }}
{{- content }}
{{- '\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' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

63
checkpoint-1000/config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"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": true,
"transformers_version": "5.7.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

12
checkpoint-1000/generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.7.0"
}

3
checkpoint-1000/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa6a5ffa325a42521faee189eed67b3922773291e206e209e90b3c770b4d4539
size 3441185608

3
checkpoint-1000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c51b9e4e783c1596ac7d185b6f7589123a938675998d0d32a5f077dfa2dfefd
size 6882572207

3
checkpoint-1000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
size 14645

3
checkpoint-1000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03766410d0ee20761a88c2327709b696e608f6be1dc35ba4d82dcb2eea2325f7
size 1465

3
checkpoint-1000/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

30
checkpoint-1000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"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": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

234
checkpoint-1000/trainer_state.json Normal file
View File

@@ -0,0 +1,234 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.16024998998437562,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"entropy": 2.223189059495926,
"epoch": 0.008012499499218782,
"grad_norm": 2.875,
"learning_rate": 1.9842973882390643e-05,
"loss": 2.3428109741210936,
"mean_token_accuracy": 0.4963963569700718,
"num_tokens": 305366.0,
"step": 50
},
{
"entropy": 2.188130117058754,
"epoch": 0.016024998998437564,
"grad_norm": 3.328125,
"learning_rate": 1.96827431501362e-05,
"loss": 2.225358734130859,
"mean_token_accuracy": 0.5110921229422093,
"num_tokens": 605042.0,
"step": 100
},
{
"entropy": 2.197347580194473,
"epoch": 0.024037498497656344,
"grad_norm": 3.453125,
"learning_rate": 1.952251241788175e-05,
"loss": 2.2299420166015627,
"mean_token_accuracy": 0.5093490639328957,
"num_tokens": 906888.0,
"step": 150
},
{
"entropy": 2.1913950395584108,
"epoch": 0.03204999799687513,
"grad_norm": 2.90625,
"learning_rate": 1.9362281685627303e-05,
"loss": 2.210995941162109,
"mean_token_accuracy": 0.5097909501194954,
"num_tokens": 1213125.0,
"step": 200
},
{
"entropy": 2.1611998677253723,
"epoch": 0.040062497496093905,
"grad_norm": 3.25,
"learning_rate": 1.920205095337286e-05,
"loss": 2.1867474365234374,
"mean_token_accuracy": 0.5154410660266876,
"num_tokens": 1509026.0,
"step": 250
},
{
"entropy": 2.168051454424858,
"epoch": 0.04807499699531269,
"grad_norm": 2.9375,
"learning_rate": 1.904182022111841e-05,
"loss": 2.190071716308594,
"mean_token_accuracy": 0.5156884534657001,
"num_tokens": 1806850.0,
"step": 300
},
{
"entropy": 2.1737154543399813,
"epoch": 0.05608749649453147,
"grad_norm": 3.421875,
"learning_rate": 1.8881589488863967e-05,
"loss": 2.199147186279297,
"mean_token_accuracy": 0.514045044630766,
"num_tokens": 2104505.0,
"step": 350
},
{
"entropy": 2.148039159178734,
"epoch": 0.06409999599375026,
"grad_norm": 3.109375,
"learning_rate": 1.872135875660952e-05,
"loss": 2.176946105957031,
"mean_token_accuracy": 0.5177112428843975,
"num_tokens": 2391088.0,
"step": 400
},
{
"entropy": 2.194890711903572,
"epoch": 0.07211249549296903,
"grad_norm": 3.28125,
"learning_rate": 1.856112802435507e-05,
"loss": 2.216288757324219,
"mean_token_accuracy": 0.5110335703194141,
"num_tokens": 2691272.0,
"step": 450
},
{
"entropy": 2.1557786524295808,
"epoch": 0.08012499499218781,
"grad_norm": 4.15625,
"learning_rate": 1.8400897292100627e-05,
"loss": 2.1812680053710936,
"mean_token_accuracy": 0.5176697050035,
"num_tokens": 2991855.0,
"step": 500
},
{
"entropy": 2.1708167713880537,
"epoch": 0.08813749449140659,
"grad_norm": 4.34375,
"learning_rate": 1.824066655984618e-05,
"loss": 2.1921002197265627,
"mean_token_accuracy": 0.5156507430970669,
"num_tokens": 3295049.0,
"step": 550
},
{
"entropy": 2.1686314886808393,
"epoch": 0.09614999399062538,
"grad_norm": 2.875,
"learning_rate": 1.8080435827591735e-05,
"loss": 2.1914617919921877,
"mean_token_accuracy": 0.5139613692462445,
"num_tokens": 3597206.0,
"step": 600
},
{
"entropy": 2.15742906332016,
"epoch": 0.10416249348984416,
"grad_norm": 3.109375,
"learning_rate": 1.7920205095337287e-05,
"loss": 2.174853973388672,
"mean_token_accuracy": 0.5159518288075924,
"num_tokens": 3905268.0,
"step": 650
},
{
"entropy": 2.162363375425339,
"epoch": 0.11217499298906294,
"grad_norm": 3.171875,
"learning_rate": 1.7759974363082843e-05,
"loss": 2.184231872558594,
"mean_token_accuracy": 0.516631413847208,
"num_tokens": 4207934.0,
"step": 700
},
{
"entropy": 2.1516289287805557,
"epoch": 0.12018749248828171,
"grad_norm": 3.609375,
"learning_rate": 1.7599743630828395e-05,
"loss": 2.167020263671875,
"mean_token_accuracy": 0.516358617246151,
"num_tokens": 4515774.0,
"step": 750
},
{
"entropy": 2.1549544781446457,
"epoch": 0.1281999919875005,
"grad_norm": 3.28125,
"learning_rate": 1.7439512898573947e-05,
"loss": 2.181917877197266,
"mean_token_accuracy": 0.5182220858335495,
"num_tokens": 4814709.0,
"step": 800
},
{
"entropy": 2.1532615756988527,
"epoch": 0.1362124914867193,
"grad_norm": 3.078125,
"learning_rate": 1.7279282166319503e-05,
"loss": 2.1659007263183594,
"mean_token_accuracy": 0.5180425970256328,
"num_tokens": 5112585.0,
"step": 850
},
{
"entropy": 2.1704017293453215,
"epoch": 0.14422499098593805,
"grad_norm": 2.921875,
"learning_rate": 1.7119051434065055e-05,
"loss": 2.1934996032714844,
"mean_token_accuracy": 0.5154964691400528,
"num_tokens": 5411369.0,
"step": 900
},
{
"entropy": 2.1349107217788696,
"epoch": 0.15223749048515683,
"grad_norm": 2.984375,
"learning_rate": 1.6958820701810608e-05,
"loss": 2.1598545837402345,
"mean_token_accuracy": 0.5208920259773732,
"num_tokens": 5707060.0,
"step": 950
},
{
"entropy": 2.1541705918312073,
"epoch": 0.16024998998437562,
"grad_norm": 3.203125,
"learning_rate": 1.6798589969556163e-05,
"loss": 2.170956573486328,
"mean_token_accuracy": 0.5204938448965549,
"num_tokens": 6004079.0,
"step": 1000
}
],
"logging_steps": 50,
"max_steps": 6241,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.095551986099814e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78622f63304ec0913ed0b4ea7a1b26c08a5621b3661a380d798c4ea426235671
size 5713