commit 7742610ccf4817adfcbea19df27f7081b85376e8 Author: ModelHub XC Date: Sun Aug 9 13:59:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: h4bbo/FuseLLM-112M Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..89eb73e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +FuseLLM-112M.bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseLLM-112M.bf16.gguf b/FuseLLM-112M.bf16.gguf new file mode 100644 index 0000000..ec3f5a3 --- /dev/null +++ b/FuseLLM-112M.bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7210a19f6f88e1cc5a0c93b49f7fd907bbb8e623e4c66b07335133b7899d4c +size 229719904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a763b27 --- /dev/null +++ b/README.md @@ -0,0 +1,135 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: h4bbo/FuseLLM-112M-Completion +tags: + - habbo + - code + - chatml + - sft +language: + - en +pipeline_tag: text-generation +--- + +# FuseLLM-112M (Chat) + +This is the **ChatML chat** variant of FuseLLM-112M — a 112M-parameter, from-scratch +Qwen3-architecture decoder-only model supervised-fine-tuned (SFT) on on-domain Habbo instruction +pairs derived **from the Habbo source corpus itself** (no external/teacher data). + +The base model, [h4bbo/FuseLLM-112M-Completion](https://huggingface.co/h4bbo/FuseLLM-112M-Completion), +was trained only on raw Habbo code in completion mode. Its tokenizer already shipped a Qwen3 +ChatML template, but the weights had never seen a chat turn, so chat-formatted prompts produced +poor, repetitive output. This checkpoint teaches the weights to follow ChatML turns and to **emit +`<|im_end|>`** at the end of an assistant answer (the turn terminator — conveniently the same token, +151645, the base model was trained to use as a document boundary), which is what stops the runaway +repetition. + +## Use + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "h4bbo/FuseLLM-112M" +tok = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="sdpa") + +messages = [ + {"role": "system", "content": "You are a Habbo Hotel emulator code assistant. Reply with concise, correct code or a brief explanation."}, + {"role": "user", "content": "Implement this Java method:\n```java\npublic static void sendRoomPacket(Session s, int header) { }\n```"}, +] +text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +ids = tok(text, return_tensors="pt").to(model.device) +out = model.generate(**ids, max_new_tokens=256, eos_token_id=151645, pad_token_id=151643, + do_sample=True, temperature=0.7, top_p=0.9, repetition_penalty=1.05) +print(tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True)) +``` + +It is designed for Habbo-coding instructions (method/class completion, code continuation, +doc→code). It is **not** a general assistant — outside its narrow domain it will produce poor or +repetitive output. + +## Architecture + +`Qwen3ForCausalLM`, hidden 512, 8 layers (full attention), 8 heads / 8 KV heads, intermediate +1408, vocab 151,936, max context 2048, `tie_word_embeddings=true`. Trained in bf16. + +## Training data + +10,000 ChatML conversations derived deterministically from the Habbo corpus (the same corpus the +base was trained on — 84,925 unique files, ~210M est. tokens; top languages Java 26,335 / +C# 19,048 / PHP 10,969 / ActionScript 3,801). No external data, no teacher model. Templates: + +- **Method completion** — given a method signature with empty body, return the real body. +- **Code continuation** — given a file prefix, return the real suffix. +- **Doc → method** — given a Javadoc/PHPDoc/`///` summary, return the real method. + +Distribution in this build: Java ~4,936 · C# ~3,752 · PHP ~989 · ActionScript ~323. Decompiler +noise (JD-Core `/* N:M */` line markers and `/* Location: … */` footers) is stripped. Secrets are +scrubbed to `[REDACTED]` (currently `xX!elgps`) before extraction; the training file is verified to +contain 0 secret occurrences. + +## Training config + +- Full fine-tune (no LoRA — 112M is small enough to train every weight on 24 GB). +- TRL `SFTTrainer` + `SFTConfig`, `messages` format auto-detected, ChatML applied by the base + tokenizer's chat template. `packing=False`, `max_length=2048` (model's native max position; only + 11/10,000 conversations exceed it). Full-sequence causal-LM loss (the Qwen3 chat template has no + `{% generation %}` markers, so `assistant_only_loss` is unset — at inference we prompt through + `<|im_start|>assistant\n` and stop at `<|im_end|>`). +- bf16, sdpa attention, `adamw_torch`, cosine schedule, 3 epochs, LR 2e-5, warmup 0.03, + effective batch 16 (BS 4 × GA 4), `max_grad_norm=1.0`, seed 42. 1,875 steps. +- `generation_config.json` is written with `eos_token_id=151645` (`<|im_end|>`), + `pad_token_id=151643`, `temperature=0.7`, `top_p=0.9`, `repetition_penalty=1.05`. + +## Training result + +Loss dropped from ~1.83 (step 10) to ~0.45 by the end of epoch 1 and held in the ~0.4–0.5 range +through epochs 2–3. Final: `train_loss 0.521`, `mean_token_accuracy 0.9144`, 1,875 steps, ~16.5 min +on a single RX 7900 XTX (ROCm). Verified behavior: method-completion and code-continuation prompts +produce coherent on-domain Habbo code, close the fenced block, and **stop at `<|im_end|>`**; +doc→method and free-form explanation prompts tend to ramble (see Limitations). + +## Redaction + +Secrets (currently `xX!elgps`) are scrubbed to `[REDACTED]` in all training content before +tokenisation. The output training file is checked to contain 0 occurrences. No known credentials +enter the weights. + +## License + +Released under **Apache-2.0**. See the base model +[h4bbo/FuseLLM-112M-Completion](https://huggingface.co/h4bbo/FuseLLM-112M-Completion) for its +license terms. + +## GGUF + +A non-quantized **bf16** GGUF — `FuseLLM-112M.bf16.gguf` (~220 MB, a bit-exact copy of the bf16 +safetensors weights, so truly lossless) — is included in this repo for use with +[llama.cpp](https://github.com/ggml-org/llama.cpp) / [Ollama](https://ollama.com). The ChatML chat +template and the EOS token (`<|im_end|>`, 151645) are embedded as GGUF metadata, so the model loads +in chat mode automatically. No quantized (Q4/Q5/Q8) variant is shipped here. + +Example with llama.cpp: + +```bash +llama-cli -m FuseLLM-112M.bf16.gguf -cnv \ + --temp 0.7 --top-p 0.9 --repeat-penalty 1.05 -n 256 \ + -p "Implement this Java method:\n```java\npublic static void sendRoomPacket(Session s, int h) { }\n```" +``` + +## Intended use + +Domain-specialist code assistant for the Habbo Hotel emulator ecosystem (server/client tooling). +Not affiliated with or endorsed by Sulake/Habbo. + +## Limitations + +- 112M parameters — narrow capacity; expect errors and repetition on long or off-domain prompts. +- Trained only on on-domain code-instruction pairs; not a general chat / instruction model. +- Doc→method and free-form explanation prompts often ramble past `<|im_end|>` despite + `repetition_penalty`; keep `max_new_tokens` modest and prefer the SFT templates + (method completion / code continuation). \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..70adff8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,61 @@ +{%- 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 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' }} + {%- endif %} +{%- endif %} +{%- 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" %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- 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 %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..e6798ac --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 512, + "initializer_range": 0.02, + "intermediate_size": 1408, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 2048, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 8, + "num_hidden_layers": 8, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.13.0", + "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..bdcc065 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "do_sample": true, + "eos_token_id": 151645, + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_p": 0.9, + "transformers_version": "5.13.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..0d778b4 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c43a20ce7f6a60ad0f73c159c9f50f3e1d43758c7ca91d3c4ee3d9f36e68e07a +size 447532792 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c77896b --- /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": true, + "local_files_only": false, + "model_max_length": 1010000, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}