初始化项目，由ModelHub XC社区提供模型
Model: FLY2002/onereason-llmrec-format 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
|
||||
24612
added_tokens.json
Normal file
24612
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal 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 %}
|
||||
65
config.json
Normal file
65
config.json
Normal file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"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"
|
||||
},
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 176253
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal 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": "4.52.4"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a8fe1d8bc1d3f7f4a28f3cddabbb80bbf92f91be36660c0bcefb5a938393873f
|
||||
size 1602902832
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
|
||||
size 16016554
|
||||
196914
tokenizer_config.json
Normal file
196914
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
35
trainer_log.jsonl
Normal file
35
trainer_log.jsonl
Normal file
@@ -0,0 +1,35 @@
|
||||
{"current_steps": 10, "total_steps": 360, "loss": 10.4267, "lr": 5e-06, "epoch": 0.055710306406685235, "percentage": 2.78, "elapsed_time": "0:01:00", "remaining_time": "0:35:01"}
|
||||
{"current_steps": 20, "total_steps": 360, "loss": 8.468, "lr": 9.999789047591563e-06, "epoch": 0.11142061281337047, "percentage": 5.56, "elapsed_time": "0:01:59", "remaining_time": "0:33:53"}
|
||||
{"current_steps": 30, "total_steps": 360, "loss": 7.2596, "lr": 9.974496289936769e-06, "epoch": 0.1671309192200557, "percentage": 8.33, "elapsed_time": "0:02:59", "remaining_time": "0:32:51"}
|
||||
{"current_steps": 40, "total_steps": 360, "loss": 6.6767, "lr": 9.90725746626209e-06, "epoch": 0.22284122562674094, "percentage": 11.11, "elapsed_time": "0:03:59", "remaining_time": "0:31:56"}
|
||||
{"current_steps": 50, "total_steps": 360, "loss": 6.0984, "lr": 9.798639549376946e-06, "epoch": 0.2785515320334262, "percentage": 13.89, "elapsed_time": "0:04:59", "remaining_time": "0:30:54"}
|
||||
{"current_steps": 60, "total_steps": 360, "loss": 5.9951, "lr": 9.64955842986544e-06, "epoch": 0.3342618384401114, "percentage": 16.67, "elapsed_time": "0:05:58", "remaining_time": "0:29:53"}
|
||||
{"current_steps": 70, "total_steps": 360, "loss": 5.7414, "lr": 9.461271193091971e-06, "epoch": 0.38997214484679665, "percentage": 19.44, "elapsed_time": "0:06:58", "remaining_time": "0:28:52"}
|
||||
{"current_steps": 80, "total_steps": 360, "loss": 5.6866, "lr": 9.23536551917611e-06, "epoch": 0.4456824512534819, "percentage": 22.22, "elapsed_time": "0:07:57", "remaining_time": "0:27:52"}
|
||||
{"current_steps": 90, "total_steps": 360, "loss": 5.5402, "lr": 8.973746295318499e-06, "epoch": 0.5013927576601671, "percentage": 25.0, "elapsed_time": "0:08:57", "remaining_time": "0:26:52"}
|
||||
{"current_steps": 100, "total_steps": 360, "loss": 5.3673, "lr": 8.67861955336566e-06, "epoch": 0.5571030640668524, "percentage": 27.78, "elapsed_time": "0:09:56", "remaining_time": "0:25:52"}
|
||||
{"current_steps": 110, "total_steps": 360, "loss": 5.2997, "lr": 8.352473868055746e-06, "epoch": 0.6128133704735376, "percentage": 30.56, "elapsed_time": "0:11:28", "remaining_time": "0:26:03"}
|
||||
{"current_steps": 120, "total_steps": 360, "loss": 5.3269, "lr": 7.998059372799409e-06, "epoch": 0.6685236768802229, "percentage": 33.33, "elapsed_time": "0:12:27", "remaining_time": "0:24:55"}
|
||||
{"current_steps": 130, "total_steps": 360, "loss": 5.084, "lr": 7.61836456993939e-06, "epoch": 0.724233983286908, "percentage": 36.11, "elapsed_time": "0:13:27", "remaining_time": "0:23:48"}
|
||||
{"current_steps": 140, "total_steps": 360, "loss": 5.0922, "lr": 7.2165911310299305e-06, "epoch": 0.7799442896935933, "percentage": 38.89, "elapsed_time": "0:14:26", "remaining_time": "0:22:42"}
|
||||
{"current_steps": 150, "total_steps": 360, "loss": 5.0874, "lr": 6.796126899625688e-06, "epoch": 0.8356545961002786, "percentage": 41.67, "elapsed_time": "0:15:26", "remaining_time": "0:21:37"}
|
||||
{"current_steps": 160, "total_steps": 360, "loss": 4.9658, "lr": 6.360517324226676e-06, "epoch": 0.8913649025069638, "percentage": 44.44, "elapsed_time": "0:16:26", "remaining_time": "0:20:32"}
|
||||
{"current_steps": 170, "total_steps": 360, "loss": 5.0017, "lr": 5.913435562263036e-06, "epoch": 0.947075208913649, "percentage": 47.22, "elapsed_time": "0:17:25", "remaining_time": "0:19:28"}
|
||||
{"current_steps": 180, "total_steps": 360, "loss": 4.8766, "lr": 5.458651507209518e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:18:22", "remaining_time": "0:18:22"}
|
||||
{"current_steps": 190, "total_steps": 360, "loss": 4.888, "lr": 5e-06, "epoch": 1.0557103064066853, "percentage": 52.78, "elapsed_time": "0:19:21", "remaining_time": "0:17:19"}
|
||||
{"current_steps": 200, "total_steps": 360, "loss": 4.8664, "lr": 4.541348492790482e-06, "epoch": 1.1114206128133706, "percentage": 55.56, "elapsed_time": "0:20:21", "remaining_time": "0:16:17"}
|
||||
{"current_steps": 210, "total_steps": 360, "loss": 4.8244, "lr": 4.0865644377369666e-06, "epoch": 1.1671309192200556, "percentage": 58.33, "elapsed_time": "0:21:55", "remaining_time": "0:15:39"}
|
||||
{"current_steps": 220, "total_steps": 360, "loss": 4.7554, "lr": 3.639482675773324e-06, "epoch": 1.222841225626741, "percentage": 61.11, "elapsed_time": "0:22:55", "remaining_time": "0:14:35"}
|
||||
{"current_steps": 230, "total_steps": 360, "loss": 4.8266, "lr": 3.203873100374314e-06, "epoch": 1.2785515320334262, "percentage": 63.89, "elapsed_time": "0:23:54", "remaining_time": "0:13:30"}
|
||||
{"current_steps": 240, "total_steps": 360, "loss": 4.7071, "lr": 2.783408868970071e-06, "epoch": 1.3342618384401115, "percentage": 66.67, "elapsed_time": "0:24:54", "remaining_time": "0:12:27"}
|
||||
{"current_steps": 250, "total_steps": 360, "loss": 4.7641, "lr": 2.381635430060611e-06, "epoch": 1.3899721448467965, "percentage": 69.44, "elapsed_time": "0:25:53", "remaining_time": "0:11:23"}
|
||||
{"current_steps": 260, "total_steps": 360, "loss": 4.8125, "lr": 2.0019406272005913e-06, "epoch": 1.4456824512534818, "percentage": 72.22, "elapsed_time": "0:26:53", "remaining_time": "0:10:20"}
|
||||
{"current_steps": 270, "total_steps": 360, "loss": 4.6879, "lr": 1.6475261319442553e-06, "epoch": 1.501392757660167, "percentage": 75.0, "elapsed_time": "0:27:53", "remaining_time": "0:09:17"}
|
||||
{"current_steps": 280, "total_steps": 360, "loss": 4.7018, "lr": 1.321380446634342e-06, "epoch": 1.5571030640668524, "percentage": 77.78, "elapsed_time": "0:28:52", "remaining_time": "0:08:15"}
|
||||
{"current_steps": 290, "total_steps": 360, "loss": 4.659, "lr": 1.026253704681502e-06, "epoch": 1.6128133704735377, "percentage": 80.56, "elapsed_time": "0:29:52", "remaining_time": "0:07:12"}
|
||||
{"current_steps": 300, "total_steps": 360, "loss": 4.6947, "lr": 7.646344808238904e-07, "epoch": 1.668523676880223, "percentage": 83.33, "elapsed_time": "0:30:52", "remaining_time": "0:06:10"}
|
||||
{"current_steps": 310, "total_steps": 360, "loss": 4.7309, "lr": 5.387288069080298e-07, "epoch": 1.724233983286908, "percentage": 86.11, "elapsed_time": "0:32:25", "remaining_time": "0:05:13"}
|
||||
{"current_steps": 320, "total_steps": 360, "loss": 4.7063, "lr": 3.504415701345615e-07, "epoch": 1.7799442896935933, "percentage": 88.89, "elapsed_time": "0:33:24", "remaining_time": "0:04:10"}
|
||||
{"current_steps": 330, "total_steps": 360, "loss": 4.7164, "lr": 2.0136045062305543e-07, "epoch": 1.8356545961002786, "percentage": 91.67, "elapsed_time": "0:35:11", "remaining_time": "0:03:11"}
|
||||
{"current_steps": 340, "total_steps": 360, "loss": 4.5977, "lr": 9.274253373791064e-08, "epoch": 1.8913649025069637, "percentage": 94.44, "elapsed_time": "0:37:16", "remaining_time": "0:02:11"}
|
||||
{"current_steps": 350, "total_steps": 360, "loss": 4.8068, "lr": 2.55037100632316e-08, "epoch": 1.947075208913649, "percentage": 97.22, "elapsed_time": "0:38:16", "remaining_time": "0:01:05"}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user