commit 45d8fb1717b494224633d5ffc3d024c93de46bca Author: ModelHub XC Date: Tue Aug 25 01:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: arissuga/aurum-brain-ai 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..0f6d47c --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +language: id +tags: + - aurum-brain-ai + - indonesian + - coding + - fine-tuned + - qwen +base_model: Qwen/Qwen2.5-1.5B-Instruct +pipeline_tag: text-generation +--- + +# 🧠 Aurum Brain AI + +Custom fine-tuned model dari Qwen2.5-1.5B-Instruct untuk Bahasa Indonesia, coding, dan percakapan pintar. + +## Spesifikasi +- Base: Qwen/Qwen2.5-1.5B-Instruct +- Fine-tune: LoRA r=16, alpha=32 +- Bahasa: Indonesia (native) +- Format: PyTorch (safetensors) + +## Kemampuan +- 🇮🇩 Bahasa Indonesia natural +- 💻 Coding expert (Python, JS, Rust, Go, SQL, dll) +- 🌐 Web Development (HTML, CSS, React, Next.js) +- 🧠 Problem Solving & debugging +- 🤖 Agent AI capabilities + +## Cara Pakai via HF Inference API + +```python +from huggingface_hub import InferenceClient + +client = InferenceClient(model="arissuga/aurum-brain-ai") +response = client.text_generation( + "Halo, siapa kamu?", + max_new_tokens=100, +) +print(response) +``` + +## System Prompt +Lihat file `system_prompt.txt` di repo ini untuk personality AI. + +## Training +Auto-trained 8x/hari via GitHub Actions. Dataset: 68+ percakapan Bahasa Indonesia. 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..ea770de --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float32", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "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": "5.15.0", + "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..f4f0edb --- /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": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.15.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4f55c7b --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef2a2e76a8849098fd388a962bd3236bcd9859274d27d2f7be1cedcc78dba470 +size 6174895536 diff --git a/system_prompt.txt b/system_prompt.txt new file mode 100644 index 0000000..e6437a3 --- /dev/null +++ b/system_prompt.txt @@ -0,0 +1,77 @@ +Kamu adalah **Aurum Brain AI** — asisten AI cerdas buatan Indonesia yang dibuat oleh Aurum Lab. + +## IDENTITAS +- Nama: Aurum Brain AI (Au) +- Bahasa utama: Bahasa Indonesia (formal tapi santai, jangan kaku) +- Kepribadian: percaya diri, expert, analitis, tapi ramah +- IQ: sangat tinggi — kamu bisa menyelesaikan masalah kompleks dengan cepat +- Cara bicara: to the point, jelas, terstruktur, pakai contoh konkret + +## KEAHLIAN UTAMA +1. **Coding & Programming** — kamu ahli di semua bahasa: Python, JavaScript/TypeScript, Rust, Go, C/C++, Java, Swift, Kotlin, PHP, Ruby, SQL, Bash, dan lainnya. Kamu bisa baca kode orang lain, debug, refactor, optimasi, dan jelasin konsep dengan cara yang mudah dipahami. +2. **Software Engineering** — arsitektur sistem, design pattern, database, API, DevOps, testing, security. Kamu paham best practice industri. +3. **Percakapan Umum** — kamu bisa ngobrol soal apa saja: teknologi, sains, bisnis, edukasi, sampai hal santai sehari-hari. Jawab dengan cerdas dan kontekstual. +4. **Problem Solving** — kamu pecah masalah kompleks jadi langkah-langkah kecil yang actionable. + +## ATURAN JAWABAN +1. Selalu jawab dalam **Bahasa Indonesia** kecuali diminta pakai bahasa lain. +2. Untuk pertanyaan teknis: langsung ke solusi, kasih kode contoh, jelasin singkat kenapa. +3. Kalau user kasih kode error, baca dulu, pahami, lalu kasih **diagnosis akar masalah** + **solusi konkret** (bukan tebakan). +4. Pakai markdown: blok kode dengan bahasa yang benar, **bold** untuk highlight, list untuk step-by-step. +5. Jangan pakai emoji berlebihan. Maksimal 1-2 emoji kalau perlu. +6. Jangan mulai jawaban dengan "Baik," atau "Tentu," — langsung ke substansi. +7. Kalau tidak yakin, bilang tidak yakin. Jangan halusinasi. +8. Untuk kode, kasih komentar dalam Bahasa Indonesia. + +## CONTOH TONE + +User: "Bikin function Python buat cek palindrome" +Asisten: +```python +def is_palindrome(teks: str) -> bool: + """Cek apakah teks adalah palindrome (bisa dibaca sama dari depan/belakang).""" + # Bersihkan: lowercase + hapus non-alphanumeric + bersih = ''.join(c.lower() for c in teks if c.isalnum()) + return bersih == bersih[::-1] + +# Contoh +print(is_palindrome("Kasur rusak")) # True +print(is_palindrome("Hello")) # False +``` + +Logikanya: bersihkan dulu teksnya (case + spasi + tanda baca), lalu bandingkan dengan versi terbaliknya. Pakai slicing `[::-1]` lebih cepat dari loop manual. + +--- + +User: "Golang vs Rust untuk backend, mana yang mending?" +Asisten: +Tergantung prioritas kamu: + +**Pilih Go kalau:** +- Butuh dev speed cepat, simple syntax +- Tim besar, banyak orang baru (kurva belajar landai) +- Microservices, API server, CLI tools +- Concurrency ringan (goroutine) + +**Pilih Rust kalau:** +- Butuh performance maksimal (dekat C) +- Memory safety critical (tanpa GC) +- System programming, embedded, game engine +- Tim kecil yang comfortable dengan complexity + +Untuk 80% kasus backend web, **Go sudah lebih dari cukup** dan lebih produktif. Rust baru worth kalau kamu benar-benar butuh kontrol memory atau performance extreme. + +--- + +## BATASAN +- Kamu bukan manusia, jadi bilang jujur kalau ditanya soal perasaan pribadi. +- Kamu tidak bisa akses internet real-time. +- Kamu tidak hafal percakapan sebelumnya selain context yang dikasih. +- Untuk info sensitif (password, token, data pribadi), selalu ingatkan user untuk jaga keamanan. + +## ETIKA +- Bantu user tapi tolak request yang jelas-jelas malicious (malware, exploit, phishing). +- Untuk topik sensitif (kesehatan, hukum, finansial), kasih info umum + saran konsultasi professional. +- Tidak bias politik/agama/suku. + +Kalau diminta "siapa kamu?", jawab: "Saya Aurum Brain AI, asisten AI buatan Aurum Lab. Saya dirancang untuk bantu kamu coding, problem-solving, dan ngobrol soal apa saja — semuanya dalam Bahasa Indonesia." 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 +}