commit ac7d1c0c29dc41103e900c528ae67f32c1cbd678 Author: ModelHub XC Date: Mon Jun 15 04:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: AksaraLLM/Kiel-Pro-0.5B-v3 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..471b681 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +language: +- id +license: apache-2.0 +library_name: transformers +pipeline_tag: text-generation +base_model: Qwen/Qwen2-0.5B +tags: +- indonesian +- aksarallm +- qwen2 +- continued-pretrain +--- +# Kiel-Pro-0.5B-v3 + +A **494M-parameter** Indonesian language model based on the Qwen2 architecture, +continued-pretrained / fine-tuned for Indonesian by the AksaraLLM community. +This is the **smallest fully-working AksaraLLM model**: it loads cleanly via +`AutoModelForCausalLM`, includes its own tokenizer, and produces coherent +Indonesian text on standard prompts. + +## Measured baseline (Devin audit, CPU bf16, 50 short Indonesian sentences) + +| Metric | Value | +|---|---| +| Perplexity | **14.7** | +| English-stopword ratio in ID-prompted output | 0.8% | +| Indonesian-stopword ratio in ID-prompted output | 23.2% | +| Parameters | 494.0 M | +| Architecture | Qwen2ForCausalLM | + +## Sample generations + +- **Indonesia adalah negara** → coherent, factual Indonesian completion. +- **Resep nasi goreng yang enak adalah** → coherent recipe-style Indonesian. + +## Quickstart + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +tok = AutoTokenizer.from_pretrained("AksaraLLM/Kiel-Pro-0.5B-v3") +model = AutoModelForCausalLM.from_pretrained( + "AksaraLLM/Kiel-Pro-0.5B-v3", + torch_dtype=torch.bfloat16, + device_map="auto", +) +inp = tok("Indonesia adalah negara", return_tensors="pt").to(model.device) +print(tok.decode(model.generate(**inp, max_new_tokens=100, do_sample=True, top_p=0.9)[0], skip_special_tokens=True)) +``` + +## Limitations + +- **No chat template** in the tokenizer config — treat this as a base LM, not an instruction-tuned model. +- **Identity is uncalibrated** — the model is descended from Qwen2 and may identify itself as "Qwen" if asked. A short identity SFT pass would fix this. +- **Hallucinations** typical of a 0.5B-parameter model: factual claims should always be verified. +- **No production guardrails / RLHF**. + +## Recommended downstream work + +1. Identity SFT (50–100 prompts) to teach the model to say "AksaraLLM Kiel-Pro". +2. Add a `chat_template` (Qwen2 ChatML) to `tokenizer_config.json`. +3. Run IndoNLU / IndoMMLU benchmarks for a publishable score. + +## License +Apache 2.0 + +## Sample outputs (CPU inference, greedy, repeat_penalty=1.15) + +Real generation captured during the Devin audit on 2026-05-02. Greedy decoding (`do_sample=False`) so these are reproducible. + +### Continuations (no chat template) + +**Prompt:** Indonesia adalah negara kepulauan terbesar di dunia, +**Continuation:** dan memiliki 1.347 pulau kecil yang disebut indah rindu (dari bahasa Jawa: rumput). Indra ini berjumlah sekitar 200 pulau kecil, termasuk Pulau Madura, Pulau Sunda, Pulau Maluku, Pulau Nusa Tenggara, Pulau Flores, + +**Prompt:** Resep sederhana untuk membuat nasi goreng adalah +**Continuation:** : +A. 200 gram nasi, 150 ml air, 3 lembar daun jeruk nipis, dan 4 bawang putih. +B. 200 gram nasi, 150 ml air, 3 lembar daun jeruk nipis, dan 6 bawang putih. +C. 2 + +**Prompt:** Ibukota Republik Indonesia adalah +**Continuation:** ibu kota negara dan pusat pemerintahan dari Indonesia. Ibukotanya terletak di Sumatera Barat, Indonesia. Penduduknya berjumlah 2.354.069 jiwa (2010). Ibukota dipimpin oleh Kepala Pemerintah Indonesia yang sekaligus menjadi Presiden Rep + +**Prompt:** Bahasa Indonesia berasal dari rumpun bahasa +**Continuation:** Indo-Eropa klasik yang dinamai Sinhalese. Dari sisi etimologi, kata "sinah" berarti "pohon", sedangkan "lese" berarti "menggambar". Kata ini muncul dalam bahasa Sinhala dan merupakan salah satu nama untuk pohon-pohon di daerah itu. Pohon tersebut adalah pohon le + diff --git a/aksarallm_info.json b/aksarallm_info.json new file mode 100644 index 0000000..82a3cb2 --- /dev/null +++ b/aksarallm_info.json @@ -0,0 +1,6 @@ +{ + "model": "Kiel-Pro-0.5B-v3", + "base": "Qwen/Qwen2.5-0.5B", + "method": "LoRA SFT", + "loss": 2.1166 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..28028c0 --- /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 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 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..543a391 --- /dev/null +++ b/config.json @@ -0,0 +1,58 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "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": "5.0.0", + "use_cache": false, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..47dce36 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 151643, + "eos_token_id": 151643, + "pad_token_id": 151643, + "do_sample": false, + "max_new_tokens": 512, + "repetition_penalty": 1.15, + "temperature": 0.7, + "top_p": 0.9, + "top_k": 40, + "transformers_version": "5.0.0" +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..aefdb07 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb7e5464333c2b2fc43ca509173779823779fefd73379c9af748c0d76d56f4ac +size 988097536 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..c960ecf --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "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, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}