commit fcddb73dee3e2eaa144bf994110c557d879463f1 Author: ModelHub XC Date: Mon May 4 16:24:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Stevefocs/MyGemmaNPC Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5e87a1 --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +base_model: google/gemma-3-270m-it +library_name: transformers +model_name: MyGemmaNPC +tags: +- generated_from_trainer +- sft +- trl +licence: license +--- + +# Model Card for MyGemmaNPC + +This model is a fine-tuned version of [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="Stevefocs/MyGemmaNPC", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with SFT. + +### Framework versions + +- TRL: 1.3.0 +- Transformers: 5.0.0 +- Pytorch: 2.10.0+cu128 +- Datasets: 4.8.5 +- Tokenizers: 0.22.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1117055 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,47 @@ +{{ bos_token }} +{%- if messages[0]['role'] == 'system' -%} + {%- if messages[0]['content'] is string -%} + {%- set first_user_prefix = messages[0]['content'] + ' + +' -%} + {%- else -%} + {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' + +' -%} + {%- endif -%} + {%- set loop_messages = messages[1:] -%} +{%- else -%} + {%- set first_user_prefix = "" -%} + {%- set loop_messages = messages -%} +{%- endif -%} +{%- for message in loop_messages -%} + {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} + {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }} + {%- endif -%} + {%- if (message['role'] == 'assistant') -%} + {%- set role = "model" -%} + {%- else -%} + {%- set role = message['role'] -%} + {%- endif -%} + {{ '' + role + ' +' + (first_user_prefix if loop.first else "") }} + {%- if message['content'] is string -%} + {{ message['content'] | trim }} + {%- elif message['content'] is iterable -%} + {%- for item in message['content'] -%} + {%- if item['type'] == 'image' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type") }} + {%- endif -%} + {{ ' +' }} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{'model +'}} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..436e93d --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "transformers_version": "5.0.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c652aad --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 106 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.0.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0117ec1 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a230f119ce0c90adcb6daf005f52dbca4775a23471450a6e2e7668d8bc98d5df +size 536223056 diff --git a/runs/Apr29_06-52-15_6ec619e311b7/events.out.tfevents.1777445535.6ec619e311b7.999.0 b/runs/Apr29_06-52-15_6ec619e311b7/events.out.tfevents.1777445535.6ec619e311b7.999.0 new file mode 100644 index 0000000..bd0648d --- /dev/null +++ b/runs/Apr29_06-52-15_6ec619e311b7/events.out.tfevents.1777445535.6ec619e311b7.999.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d5eef0e001eca66283744e9deaa60ec09f39a3bcb0eafbb7f737ea34e73ae5d +size 17619 diff --git a/runs/Apr29_07-16-12_6ec619e311b7/events.out.tfevents.1777446972.6ec619e311b7.999.1 b/runs/Apr29_07-16-12_6ec619e311b7/events.out.tfevents.1777446972.6ec619e311b7.999.1 new file mode 100644 index 0000000..0be748d --- /dev/null +++ b/runs/Apr29_07-16-12_6ec619e311b7/events.out.tfevents.1777446972.6ec619e311b7.999.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca434df3203b6b7badb339c3923f3e24024b0f76f58e829a3fae6b80fd9c08c3 +size 17619 diff --git a/runs/Apr29_07-25-35_6ec619e311b7/events.out.tfevents.1777447535.6ec619e311b7.999.2 b/runs/Apr29_07-25-35_6ec619e311b7/events.out.tfevents.1777447535.6ec619e311b7.999.2 new file mode 100644 index 0000000..3728554 --- /dev/null +++ b/runs/Apr29_07-25-35_6ec619e311b7/events.out.tfevents.1777447535.6ec619e311b7.999.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5af330a8bcba463fcad148a9a3152b2eab7291e1ab507bdef9056145e78cdf +size 10119 diff --git a/runs/Apr29_07-33-55_6ec619e311b7/events.out.tfevents.1777448035.6ec619e311b7.999.3 b/runs/Apr29_07-33-55_6ec619e311b7/events.out.tfevents.1777448035.6ec619e311b7.999.3 new file mode 100644 index 0000000..f5caaad --- /dev/null +++ b/runs/Apr29_07-33-55_6ec619e311b7/events.out.tfevents.1777448035.6ec619e311b7.999.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9cd988880b217707d8617bfef6f7032be7b101545ec68741fb9915acc44764 +size 10119 diff --git a/runs/Apr29_08-49-10_133a002c0151/events.out.tfevents.1777452550.133a002c0151.626.0 b/runs/Apr29_08-49-10_133a002c0151/events.out.tfevents.1777452550.133a002c0151.626.0 new file mode 100644 index 0000000..1010ea9 --- /dev/null +++ b/runs/Apr29_08-49-10_133a002c0151/events.out.tfevents.1777452550.133a002c0151.626.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d4993b0a7f77efd1eb7bd747b7a5ff80c5db85348b84d1b7dd8a353ed3cbee +size 10119 diff --git a/runs/Apr29_10-39-59_db5b3868d54b/events.out.tfevents.1777459199.db5b3868d54b.489.0 b/runs/Apr29_10-39-59_db5b3868d54b/events.out.tfevents.1777459199.db5b3868d54b.489.0 new file mode 100644 index 0000000..aca0ff3 --- /dev/null +++ b/runs/Apr29_10-39-59_db5b3868d54b/events.out.tfevents.1777459199.db5b3868d54b.489.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8776f1f4bc0ab6cdf44fbde097a89ea5fa78d97e89147560d40890718a586d7e +size 10119 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..899af07 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497 +size 33384443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7202584 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,24 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "" + }, + "pad_token": "", + "padding_side": "left", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..d4e2602 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11898a8eb71ad23eb499da843b572c35af46c633167d515f08d09e7c789e3886 +size 5713