From d5b078487f3e1d67aa8931878034f321f09c3b13 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 5 Aug 2026 00:01:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: h4bbo/FuseLLM-112M-Completion Source: Original Platform --- .gitattributes | 38 ++++++++++++++++ README.md | 100 +++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 61 +++++++++++++++++++++++++ config.json | 44 ++++++++++++++++++ generation_config.json | 11 +++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 30 +++++++++++++ 8 files changed, 290 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..771664e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +gguf/FuseLLM-112M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/FuseLLM-112M.fp16.gguf 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..1da2689 --- /dev/null +++ b/README.md @@ -0,0 +1,100 @@ +--- +library_name: transformers +license: other # TODO: set the license you want to release this model under +language: + - code +tags: + - qwen3 + - causal-lm + - code-completion + - habbo + - from-scratch +--- + +# FuseLLM-112M + +A small **112M-parameter decoder-only language model trained from scratch** (no base +checkpoint, no LoRA) on a corpus of Habbo emulator / game-server source code. The +goal is a tiny, fast model for **code completion** in that Java codebase, not a +general-purpose or instruction-following model. + +## Model details + +| | | +|---|---| +| Architecture | Qwen3 (decoder-only causal LM) | +| Parameters | ~112M (tied input/output embeddings) | +| Hidden size | 512 | +| Layers | 8 (all full attention) | +| Attention heads | 8 (8 KV heads) | +| Vocab size | 151,936 | +| Max context | 2048 | +| Precision | float32 (safetensors) | +| Training | From scratch, 4 epochs, 16,188 steps | +| Final train loss | ~0.58 | + +`tie_word_embeddings: true` — the output `lm_head` shares the input embedding +matrix, so checkpoints store only one copy. This is expected, not a missing weight. + +## Intended use + +- **Code completion** for Habbo-style Java server code (raw prompt → continuation). +- Local experimentation / distillation base. + +## What it is NOT + +- **Not instruction-tuned / not a chat model.** It was trained only on raw source + code, never on chat/instruction data. +- The Qwen3 ChatML chat template is included (it ships with the tokenizer) for + tokenizer/tool compatibility, but the model has **not** learned to follow chat + turns. Passing chat-formatted prompts will produce poor, often repetitive output. + Use it in **completion mode**, not conversation mode. + +## Usage + +### transformers (recommended for completion) + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +m = AutoModelForCausalLM.from_pretrained("h4bbo/FuseLLM-112M") +tok = AutoTokenizer.from_pretrained("h4bbo/FuseLLM-112M") + +prompt = "public class Room {\n public void onEnter(Player p) {\n " +ids = tok(prompt, return_tensors="pt").input_ids +out = m.generate(ids, max_new_tokens=64, do_sample=False, + repetition_penalty=1.1, pad_token_id=tok.eos_token_id) +print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True)) +``` + +### llama.cpp (completion mode) + +No GGUF is shipped in this repo. The HF model is **verified** to convert and run in +`llama.cpp`; generate the GGUF locally: + +```bash +# 1) convert HF -> lossless fp16 GGUF +python convert_hf_to_gguf.py h4bbo/FuseLLM-112M --outtype f16 \ + --model-name FuseLLM-112M --outfile FuseLLM-112M.fp16.gguf +# (optional) 4-bit quantize +llama-quantize FuseLLM-112M.fp16.gguf FuseLLM-112M.Q4_K_M.gguf Q4_K_M + +# 2) completion mode — pass the raw code seed, do NOT use chat/conversation mode. +llama-cli -m FuseLLM-112M.Q4_K_M.gguf -cnv -st --no-jinja \ + -f seed.txt -n 64 --temp 0.0 --repeat-penalty 1.1 --no-display-prompt < /dev/null +``` + +`--no-jinja` keeps the prompt raw (the embedded chat template exists but the model +isn't chat-tuned, so conversation mode is not meaningful for this model). + +## Files + +- `model.safetensors`, `config.json`, `generation_config.json` — HF model +- `tokenizer.json`, `tokenizer_config.json`, `chat_template.jinja` — tokenizer + ChatML template + +## Notes + +- Small model + limited-domain corpus: expect repetition on long generations; use + a repetition penalty and keep continuations short. +- Trained from scratch, so this is fully independent of any upstream Qwen weights. + The Qwen3 architecture/tokenizer are reused for compatibility. \ 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..93b190f --- /dev/null +++ b/config.json @@ -0,0 +1,44 @@ +{ + "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, + "_name_or_path": "FuseLLM-112M" +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9361898 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151645 + ], + "output_attentions": false, + "output_hidden_states": false, + "pad_token_id": 151643, + "transformers_version": "5.13.0", + "use_cache": false +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..74bed1d --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ebdb08b1e9f44ccf2bf768c7425bbb3971ecfd4f08fc59b5083b718a0d63fb +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..cb87962 --- /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": 1010000, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}