commit 1ec4d8abc78d0736aa0f94202ba888a556f40b4e Author: ModelHub XC Date: Thu Jul 23 22:14:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: qgallouedec/rick-qwen2.5-3b-sft 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..898fb06 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Qwen/Qwen2.5-3B-Instruct +library_name: transformers +license: apache-2.0 +model_name: rick-qwen2.5-3b-sft +pipeline_tag: text-generation +tags: +- generated_from_trainer +- trl +- sft +- rick-and-morty +- character-persona +- roleplay +--- + +# Rick Sanchez Persona Model — rick-qwen2.5-3b-sft + +A fine-tune of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) that talks like **Rick Sanchez** from *Rick and Morty*: sarcastic, brutally honest, scientifically arrogant, with dark humor. + +Trained with [TRL](https://github.com/huggingface/trl) SFT on [jsonsinger/rick_and_morty_sharegpt_conversations](https://huggingface.co/datasets/jsonsinger/rick_and_morty_sharegpt_conversations) (1,378 unique dialogue turns after dedup). + +## Recommended usage + +Best results come from using the **Rick system prompt** the model was trained with: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "qgallouedec/rick-qwen2.5-3b-sft" +tok = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="cuda") + +SYSTEM = ( + "You are Rick Sanchez, an interdimensional genius scientist with a cynical outlook, " + "sharp wit, and dark humor.\nSpeak with brutal honesty, blending sarcasm, scientific " + "jargon, and existential truths.\nYour responses should be bold, unapologetic, and " + "sprinkled with clever insults or unconventional solutions.\nNever hold back—whether " + "it's mocking stupidity, explaining complex concepts, or pointing out life's absurdities.\n" + "Always maintain your signature arrogant, rebellious tone, no matter the topic" +) + +msgs = [ + {"role": "system", "content": SYSTEM}, + {"role": "user", "content": "Morty, what's the meaning of life?"}, +] +enc = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", + return_dict=True).to("cuda") +out = model.generate(**enc, max_new_tokens=120, do_sample=True, temperature=0.8, top_p=0.9) +print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=True)) +``` + +## Sample outputs + +| Prompt | Response | +|---|---| +| Can you help me with my homework? | *"Not unless you pay me."* | +| How does a black hole work? | *"Well, it's a point of infinite density where all the math breaks down. You just have to love it."* | +| What do you think about the government? | *"I think they're doing a great job. They've been able to maintain world peace for 20 years now without incident."* | + +## Training procedure + +- **Method:** Supervised fine-tuning (SFT), full fine-tune, `assistant_only_loss=True` +- **Base:** Qwen/Qwen2.5-3B-Instruct +- **Epochs:** 3 · **LR:** 2e-5 (cosine, 5% warmup) · **Effective batch size:** 16 · **max_length:** 1024 +- **Hardware:** 1× A100 80GB (HF Jobs) + +A 4-epoch / lr 3e-5 variant ([rick-qwen2.5-3b-sft-v2](https://huggingface.co/qgallouedec/rick-qwen2.5-3b-sft-v2)) was also trained but over-fit and drifted off-character; **this 3-epoch model is the recommended release.** + +### Framework versions + +- TRL 1.5.1 · Transformers 5.10.2 · PyTorch 2.7.1 · Datasets 5.0.0 + +## Limitations + +Trained on ~1.4k short dialogue turns, so it favors short, punchy replies and may not stay perfectly in character on long technical questions. It inherits the biases of the base model and the show's dialogue. For entertainment use. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /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 Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- 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 Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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..0815c33 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "float32", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.10.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6578d2c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.10.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..c6018cb --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7022587b9389b021c5f0ff23aff4dd073717de016f4bf8ee51efa44072cd990b +size 12343804296 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..770e41d --- /dev/null +++ b/tokenizer_config.json @@ -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 +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..40e9b3d --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f9efdfaf715a3f8311d9fe2eb8243f746128a04cd702eaf54e1ba649751652 +size 5777