commit 9528a6835b89d8b8793b9831a7f03e9a7adcd00e Author: ModelHub XC Date: Sun Jul 12 17:48:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: sdavies/globe-theatre-qwen25-3b-merged 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..d1b6cd9 --- /dev/null +++ b/README.md @@ -0,0 +1,127 @@ +--- +license: apache-2.0 +base_model: +- Qwen/Qwen2.5-3B-Instruct +tags: +- qwen2.5 +- transformers +- comedy +- creative-writing +- shakespeare +- merged +- text-generation-inference +- hackathon +- build-small +library_name: transformers +--- +# 🎭 The Tragedy of the Group Chat: Merged Model + +A standalone merged Transformers version of The Tragedy of the Group Chat. + +This repository combines the Qwen2.5-3B-Instruct base model with the trained LoRA adapter into a single deployable **Transformers** model. + +**Most language models try to solve your problems.** + +**The Tragedy of the Group Chat** assumes your problems deserve a **badly performed Elizabethan stage production** instead. + +> You forgot to buy milk. Again. Everyone is angry. A sensible person would apologise. +> This model instead assembles an Elizabethan comedy troupe to make the situation considerably worse. + + +![image](https://cdn-uploads.huggingface.co/production/uploads/6720fc25ebc007333bffab63/DacI6UautUOQOSB18Rdf7.png) + +## About the project + +The Tragedy of the Group Chat was created for the Hugging Face Build-Small Hackathon (June 2026). + +The project explored how much personality and structure can be taught to a relatively small local model through careful fine-tuning and iterative evaluation. + +Rather than building a general-purpose assistant, the goal was to transform tiny modern inconveniences into exaggerated theatrical comedy scenes. + +## Repository structure + +The project consists of three related repositories: +- **LoRA adapter**: The original PEFT fine-tuning.
+- **Merged model (this repository)**: A standalone Transformers version of the model.
+- **GGUF edition**: A quantised deployment build for llama.cpp and local inference. + +## What does it do? + +Given a small modern grievance, the model produces a short comic scene in the style of a badly organised Elizabethan theatre company. + +Typical outputs include: + +* TITLE +* DRAMATIS PERSONAE +* SCENE +* THOU MUST CHOOSE + +The intended voice combines influences from: + +* Shakespeare +* Blackadder +* Monty Python +* British sitcoms +* Amateur dramatic societies + +## Performance + +The underlying fine-tuned model achieved **56/80** on a held-out ten-prompt manual benchmark. The base Qwen2.5-3B-Instruct model scored **36/80** using the same evaluation procedure. + +The merged model preserves the behaviour of the LoRA adapter while simplifying deployment. + +## Intended use + +The model is intended for entertainment and creative text generation. + +It performs best on: + +* everyday annoyances +* social awkwardness +* household disasters +* transport failures +* office politics +* mildly haunted appliances +* inexplicably judgemental animals + +## Limitations + +The model intentionally prioritises style over factual accuracy. + +Recurring characters and running jokes are expected behaviour. + +The model performs best on small frustrations rather than major life events. + +## Loading + +This repository contains a standalone Transformers model and can be loaded directly with the Hugging Face Transformers library. + +## Build process + +This model was created by: + +Qwen2.5-3B-Instruct + +↓ + +LoRA fine-tuning + +↓ + +PEFT merge-and-unload + +↓ + +Standalone Transformers model + +This merged model serves as the source for the GGUF deployment build. + + +## Try the model + +- 🎭 [Interactive demo](https://huggingface.co/spaces/sdavies/tragedy-of-the-group-chat) + +## Related repositories + +- [LoRA adapter](https://huggingface.co/sdavies/globe-theatre-qwen25-3b-lora) +- [GGUF edition](https://huggingface.co/sdavies/globe-theatre-qwen25-3b-gguf) \ No newline at end of file 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..0410246 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "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": null, + "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": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e0029cc --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "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..96e90a6 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c399a7e543cde476f19af5192f8bc886d456afb2f2fd9278f50a7aa11b33e7 +size 6171926680 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 +}