Файл	Описание
`config.json`	конфиг LLM
`model.safetensors`	Qwen3-0.6B + LoRA (merged)
`tokenizer.json` / `tokenizer_config.json`	токенизатор
`projector.safetensors`	vision-проектор (768→2048→2048→1024)
`clip_vision/`	CLIP ViT-B/32 vision encoder

Быстрый старт (text only)

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "AuroraSystem/Aurora-Clary-0.6",
    subfolder="merged", torch_dtype="auto", device_map="auto"
)
tok = AutoTokenizer.from_pretrained("AuroraSystem/Aurora-Clary-0.6", subfolder="merged")

prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Напиши факториал на Python"}],
    tokenize=False, add_generation_prompt=True
)
out = model.generate(tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=200)
print(tok.decode(out[0], skip_special_tokens=True))

Быстрый старт (Vision)

Для картинок нужен CLIP + проектор. Архитектура:

Image -> CLIP ViT-B/32 (frozen) -> Projector (768→2048→2048→1024) -> [49 tokens]
Text  -> Qwen3 embeddings                                        -> [tokens]
       [vision_tokens + text_tokens] -> Qwen3-0.6B -> ответ

Возможности

Текст: инструкции, знания, русский + английский
Код: генерация Python
Математика
Суммаризация (EN + RU)
Vision: описание изображений, цвета
Режим /think (Qwen3 thinking)

Ограничения

Вижн OCR слабый (мелкий текст не читает)
Системные промпты не обучались
База — Qwen3-0.6B, потолок соответствует 0.6B-классу

Альтернативные форматы

GGUF (для llama.cpp / LM Studio / Ollama): AuroraSystem/Clary-0.6-0.6B-GGUF

Лицензия

Apache-2.0. Base — Qwen3-0.6B (Apache-2.0).

English

Files

File	Description
`config.json`	LLM config
`model.safetensors`	Qwen3-0.6B + LoRA (merged)
`tokenizer.json` / `tokenizer_config.json`	tokenizer
`projector.safetensors`	vision projector (768→2048→2048→1024)
`clip_vision/`	CLIP ViT-B/32 vision encoder

Quick start (text only)

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "AuroraSystem/Aurora-Clary-0.6",
    subfolder="merged", torch_dtype="auto", device_map="auto"
)
tok = AutoTokenizer.from_pretrained("AuroraSystem/Aurora-Clary-0.6", subfolder="merged")

prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Write a Python factorial function"}],
    tokenize=False, add_generation_prompt=True
)
out = model.generate(tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=200)
print(tok.decode(out[0], skip_special_tokens=True))

Quick start (Vision)

For images you need CLIP + projector. Architecture:

Image -> CLIP ViT-B/32 (frozen) -> Projector (768→2048→2048→1024) -> [49 tokens]
Text  -> Qwen3 embeddings                                       -> [tokens]
       [vision_tokens + text_tokens] -> Qwen3-0.6B -> answer

Capabilities

Text: instructions, knowledge, Russian + English
Code: Python generation
Math
Summarization (EN + RU)
Vision: image description, colors
/think mode (Qwen3 thinking)

Limitations

OCR is weak (small text not recognized)
System prompts were not trained
Base is Qwen3-0.6B, ceiling matches 0.6B class

Alternative formats

GGUF (for llama.cpp / LM Studio / Ollama): AuroraSystem/Clary-0.6-0.6B-GGUF

License

Apache-2.0. Base — Qwen3-0.6B (Apache-2.0).

AuroraSystem/Clary-0.6-0.6B

Aurora Clary 0.6 Safetensors

Файлы

Быстрый старт (text only)

Быстрый старт (Vision)

Возможности

Ограничения

Альтернативные форматы

Лицензия

English

Files

Quick start (text only)

Quick start (Vision)

Capabilities

Limitations

Alternative formats

License

AuroraSystem/
Clary-0.6-0.6B