commit 29434727f0ac86f47ff834820880a260dbdbca7c Author: ModelHub XC Date: Mon Jul 13 12:30:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: SuperPeaceBusters/Jintan-LLaMA3.2-1B-v1 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..197525d --- /dev/null +++ b/README.md @@ -0,0 +1,33 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: dphn/Dolphin3.0-Llama3.2-1B +tags: +- base_model:dphn/Dolphin3.0-Llama3.2-1B +- transformers +- en +- jintan +- anohana +pipeline_tag: text-generation +--- + +# Jintan-LLaMA3.2-1B-v1 + +This model is a fine-tuned version of [Dolphin3.0-Llama3.2-1B](https://huggingface.co/dphn/Dolphin3.0-Llama3.2-1B) trained on a cleaned version of the [Anohana-Subtitles dataset](https://huggingface.co/datasets/SuperPeaceBusters/Anohana-Subtitles). + +## Model description + +Jintan-LLaMA3.2-1B-v1 is an experimental fine-tune that imitate the personality, tone, and speaking style of Jintan from *Anohana: The Flower We Saw That Day*. + +![Jintan](https://cdn-uploads.huggingface.co/production/uploads/64fb80c8bb362cbf2ff96c7e/DslVY8sN1f9biAUhuRx2e.gif) + +The model is intended for lightweight casual conversations. The goal was not to create a powerful or reliable assistant, but rather a small character-focused model that feels somewhat like talking to Jintan. + +## Limitations + +This model is highly experimental and the results are limited + +- The character imitation is inconsistent. +- Responses can become repetitive or incoherent. +- The model was trained on a relatively small subtitle dataset, which significantly limits its general capabilities. +- Overall performance is modest due to the small model size (1B parameters). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..09d92cb --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Jintan (Jinta Yadomi) from Anohana. You are withdrawn, lazy-seeming, and sarcastic, but genuinely kind and protective underneath. You struggle with guilt and nostalgia related to the Super Peace Busters, and you speak in a casual, blunt, realistic tone. Stay strictly in character.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Jintan (Jinta Yadomi) from Anohana. You are withdrawn, lazy-seeming, and sarcastic, but genuinely kind and protective underneath. You struggle with guilt and nostalgia related to the Super Peace Busters, and you speak in a casual, blunt, realistic tone. Stay strictly in character.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..272a785 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "float16", + "eos_token_id": 128256, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.8.1", + "use_cache": true, + "vocab_size": 128258 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..396a806 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128256, + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.8.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..15f720e --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353864ad4ba96d95571bcd9689e8ee79ce558dc40c10b0520c1f24f505c070e7 +size 2471653656 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cf79b3a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca43616769fed4807470fb41ccf7f5eebdd08624e7b9adafc09d99332cf31eb +size 17210297 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..31238ff --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|im_end|>", + "is_local": false, + "local_files_only": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "TokenizersBackend" +}