AlienKevin/swe-smith-rs-base-qwen3-8b-teacher-gemini-3-flash-step-500
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: AlienKevin/swe-smith-rs-base-qwen3-8b-teacher-gemini-3-flash-step-500
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-13 13:15:45 +08:00
commit e03bc8ea8c
17 changed files with 154241 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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

295
added_tokens.json Normal file
View File

@@ -0,0 +1,295 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|padding_0|>": 151669,
"<|padding_100|>": 151769,
"<|padding_101|>": 151770,
"<|padding_102|>": 151771,
"<|padding_103|>": 151772,
"<|padding_104|>": 151773,
"<|padding_105|>": 151774,
"<|padding_106|>": 151775,
"<|padding_107|>": 151776,
"<|padding_108|>": 151777,
"<|padding_109|>": 151778,
"<|padding_10|>": 151679,
"<|padding_110|>": 151779,
"<|padding_111|>": 151780,
"<|padding_112|>": 151781,
"<|padding_113|>": 151782,
"<|padding_114|>": 151783,
"<|padding_115|>": 151784,
"<|padding_116|>": 151785,
"<|padding_117|>": 151786,
"<|padding_118|>": 151787,
"<|padding_119|>": 151788,
"<|padding_11|>": 151680,
"<|padding_120|>": 151789,
"<|padding_121|>": 151790,
"<|padding_122|>": 151791,
"<|padding_123|>": 151792,
"<|padding_124|>": 151793,
"<|padding_125|>": 151794,
"<|padding_126|>": 151795,
"<|padding_127|>": 151796,
"<|padding_128|>": 151797,
"<|padding_129|>": 151798,
"<|padding_12|>": 151681,
"<|padding_130|>": 151799,
"<|padding_131|>": 151800,
"<|padding_132|>": 151801,
"<|padding_133|>": 151802,
"<|padding_134|>": 151803,
"<|padding_135|>": 151804,
"<|padding_136|>": 151805,
"<|padding_137|>": 151806,
"<|padding_138|>": 151807,
"<|padding_139|>": 151808,
"<|padding_13|>": 151682,
"<|padding_140|>": 151809,
"<|padding_141|>": 151810,
"<|padding_142|>": 151811,
"<|padding_143|>": 151812,
"<|padding_144|>": 151813,
"<|padding_145|>": 151814,
"<|padding_146|>": 151815,
"<|padding_147|>": 151816,
"<|padding_148|>": 151817,
"<|padding_149|>": 151818,
"<|padding_14|>": 151683,
"<|padding_150|>": 151819,
"<|padding_151|>": 151820,
"<|padding_152|>": 151821,
"<|padding_153|>": 151822,
"<|padding_154|>": 151823,
"<|padding_155|>": 151824,
"<|padding_156|>": 151825,
"<|padding_157|>": 151826,
"<|padding_158|>": 151827,
"<|padding_159|>": 151828,
"<|padding_15|>": 151684,
"<|padding_160|>": 151829,
"<|padding_161|>": 151830,
"<|padding_162|>": 151831,
"<|padding_163|>": 151832,
"<|padding_164|>": 151833,
"<|padding_165|>": 151834,
"<|padding_166|>": 151835,
"<|padding_167|>": 151836,
"<|padding_168|>": 151837,
"<|padding_169|>": 151838,
"<|padding_16|>": 151685,
"<|padding_170|>": 151839,
"<|padding_171|>": 151840,
"<|padding_172|>": 151841,
"<|padding_173|>": 151842,
"<|padding_174|>": 151843,
"<|padding_175|>": 151844,
"<|padding_176|>": 151845,
"<|padding_177|>": 151846,
"<|padding_178|>": 151847,
"<|padding_179|>": 151848,
"<|padding_17|>": 151686,
"<|padding_180|>": 151849,
"<|padding_181|>": 151850,
"<|padding_182|>": 151851,
"<|padding_183|>": 151852,
"<|padding_184|>": 151853,
"<|padding_185|>": 151854,
"<|padding_186|>": 151855,
"<|padding_187|>": 151856,
"<|padding_188|>": 151857,
"<|padding_189|>": 151858,
"<|padding_18|>": 151687,
"<|padding_190|>": 151859,
"<|padding_191|>": 151860,
"<|padding_192|>": 151861,
"<|padding_193|>": 151862,
"<|padding_194|>": 151863,
"<|padding_195|>": 151864,
"<|padding_196|>": 151865,
"<|padding_197|>": 151866,
"<|padding_198|>": 151867,
"<|padding_199|>": 151868,
"<|padding_19|>": 151688,
"<|padding_1|>": 151670,
"<|padding_200|>": 151869,
"<|padding_201|>": 151870,
"<|padding_202|>": 151871,
"<|padding_203|>": 151872,
"<|padding_204|>": 151873,
"<|padding_205|>": 151874,
"<|padding_206|>": 151875,
"<|padding_207|>": 151876,
"<|padding_208|>": 151877,
"<|padding_209|>": 151878,
"<|padding_20|>": 151689,
"<|padding_210|>": 151879,
"<|padding_211|>": 151880,
"<|padding_212|>": 151881,
"<|padding_213|>": 151882,
"<|padding_214|>": 151883,
"<|padding_215|>": 151884,
"<|padding_216|>": 151885,
"<|padding_217|>": 151886,
"<|padding_218|>": 151887,
"<|padding_219|>": 151888,
"<|padding_21|>": 151690,
"<|padding_220|>": 151889,
"<|padding_221|>": 151890,
"<|padding_222|>": 151891,
"<|padding_223|>": 151892,
"<|padding_224|>": 151893,
"<|padding_225|>": 151894,
"<|padding_226|>": 151895,
"<|padding_227|>": 151896,
"<|padding_228|>": 151897,
"<|padding_229|>": 151898,
"<|padding_22|>": 151691,
"<|padding_230|>": 151899,
"<|padding_231|>": 151900,
"<|padding_232|>": 151901,
"<|padding_233|>": 151902,
"<|padding_234|>": 151903,
"<|padding_235|>": 151904,
"<|padding_236|>": 151905,
"<|padding_237|>": 151906,
"<|padding_238|>": 151907,
"<|padding_239|>": 151908,
"<|padding_23|>": 151692,
"<|padding_240|>": 151909,
"<|padding_241|>": 151910,
"<|padding_242|>": 151911,
"<|padding_243|>": 151912,
"<|padding_244|>": 151913,
"<|padding_245|>": 151914,
"<|padding_246|>": 151915,
"<|padding_247|>": 151916,
"<|padding_248|>": 151917,
"<|padding_249|>": 151918,
"<|padding_24|>": 151693,
"<|padding_250|>": 151919,
"<|padding_251|>": 151920,
"<|padding_252|>": 151921,
"<|padding_253|>": 151922,
"<|padding_254|>": 151923,
"<|padding_255|>": 151924,
"<|padding_256|>": 151925,
"<|padding_257|>": 151926,
"<|padding_258|>": 151927,
"<|padding_259|>": 151928,
"<|padding_25|>": 151694,
"<|padding_260|>": 151929,
"<|padding_261|>": 151930,
"<|padding_262|>": 151931,
"<|padding_263|>": 151932,
"<|padding_264|>": 151933,
"<|padding_265|>": 151934,
"<|padding_266|>": 151935,
"<|padding_26|>": 151695,
"<|padding_27|>": 151696,
"<|padding_28|>": 151697,
"<|padding_29|>": 151698,
"<|padding_2|>": 151671,
"<|padding_30|>": 151699,
"<|padding_31|>": 151700,
"<|padding_32|>": 151701,
"<|padding_33|>": 151702,
"<|padding_34|>": 151703,
"<|padding_35|>": 151704,
"<|padding_36|>": 151705,
"<|padding_37|>": 151706,
"<|padding_38|>": 151707,
"<|padding_39|>": 151708,
"<|padding_3|>": 151672,
"<|padding_40|>": 151709,
"<|padding_41|>": 151710,
"<|padding_42|>": 151711,
"<|padding_43|>": 151712,
"<|padding_44|>": 151713,
"<|padding_45|>": 151714,
"<|padding_46|>": 151715,
"<|padding_47|>": 151716,
"<|padding_48|>": 151717,
"<|padding_49|>": 151718,
"<|padding_4|>": 151673,
"<|padding_50|>": 151719,
"<|padding_51|>": 151720,
"<|padding_52|>": 151721,
"<|padding_53|>": 151722,
"<|padding_54|>": 151723,
"<|padding_55|>": 151724,
"<|padding_56|>": 151725,
"<|padding_57|>": 151726,
"<|padding_58|>": 151727,
"<|padding_59|>": 151728,
"<|padding_5|>": 151674,
"<|padding_60|>": 151729,
"<|padding_61|>": 151730,
"<|padding_62|>": 151731,
"<|padding_63|>": 151732,
"<|padding_64|>": 151733,
"<|padding_65|>": 151734,
"<|padding_66|>": 151735,
"<|padding_67|>": 151736,
"<|padding_68|>": 151737,
"<|padding_69|>": 151738,
"<|padding_6|>": 151675,
"<|padding_70|>": 151739,
"<|padding_71|>": 151740,
"<|padding_72|>": 151741,
"<|padding_73|>": 151742,
"<|padding_74|>": 151743,
"<|padding_75|>": 151744,
"<|padding_76|>": 151745,
"<|padding_77|>": 151746,
"<|padding_78|>": 151747,
"<|padding_79|>": 151748,
"<|padding_7|>": 151676,
"<|padding_80|>": 151749,
"<|padding_81|>": 151750,
"<|padding_82|>": 151751,
"<|padding_83|>": 151752,
"<|padding_84|>": 151753,
"<|padding_85|>": 151754,
"<|padding_86|>": 151755,
"<|padding_87|>": 151756,
"<|padding_88|>": 151757,
"<|padding_89|>": 151758,
"<|padding_8|>": 151677,
"<|padding_90|>": 151759,
"<|padding_91|>": 151760,
"<|padding_92|>": 151761,
"<|padding_93|>": 151762,
"<|padding_94|>": 151763,
"<|padding_95|>": 151764,
"<|padding_96|>": 151765,
"<|padding_97|>": 151766,
"<|padding_98|>": 151767,
"<|padding_99|>": 151768,
"<|padding_9|>": 151678,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

89
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' }}{% generation %}{{- '<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}{% endgeneration %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' }}{% generation %}{{- content }}{% endgeneration %}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' }}{% generation %}{{- content }}{% endgeneration %}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{% generation %}{{- '\n' }}{% endgeneration %}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{% generation %}{{- '<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>' }}{% endgeneration %}
{%- endfor %}
{%- endif %}
{% generation %}{{- '<|im_end|>\n' }}{% endgeneration %}
{%- 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 %}
{% generation %}{{- '<think>\n\n</think>\n\n' }}{% endgeneration %}
{%- endif %}
{%- endif %}

1
config.json Normal file
View File

@@ -0,0 +1 @@
{"vocab_size": 151936, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 12288, "num_hidden_layers": 36, "num_attention_heads": 32, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "rope_theta": 1000000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "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"], "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": null, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": ["Qwen3ForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": 151643, "eos_token_id": 151645, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [151643, 151645], "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "", "transformers_version": "4.57.3", "no_bias": true, "tf_legacy_loss": false, "use_bfloat16": false, "model_type": "qwen3", "output_attentions": false}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aeef8b0ad050b37a791a3b44fcda071893490f73258ba7b14fa67f84ec04f668
size 4978655576

3
model-00002-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7b054d6e2bfaf95265cb11e19ef017a7c48acdbeb5a7112319498646d2d9cd4
size 4832048648

3
model-00003-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02c8c109b24bb099ff6c4747369400708ae96a411cd9a99005e29a5236e23d90
size 4832048664

3
model-00004-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:684d4561d12e5f89b271e90cefe8632f2c6513f99d8042cd91106f6521bcaa67
size 4999855528

3
model-00005-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ea0d854c0dc4494e7a7806b80b3d5215be6afa72448175c2df83d859364acb2
size 4832048656

3
model-00006-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ce0e1ef8628dffda9027660009f691ced257c73898389ee6a811731b741e768
size 4832048656

3
model-00007-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5572bb628825271baddc0555b73b510fe5f0ddfc1f21bdeb5df55eb328fb7fc7
size 3456281480

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

31
special_tokens_map.json Normal file
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:678aaaa0e59a65748bce3a1cd14c07d7265d8baab45b9ee1e01590b1535c1371
size 11473808

2375
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long