Spark-5M-Base-v4
Сегодня мы представляем Spark v4, базовую модель ламы с 5M параметрами, обученную на 0,7B токенах Sample-10BT из Fineweb-Edu....
Метка: Small
eMail-LM
Это модель GPT с параметром 44,64M, которая генерирует электронные письма. Чтобы использовать эту модель, загрузите model.pt и use.py...
kona2-small-3.8B
Kona2-small-3.8B is a compact 3.8-billion parameter Georgian language model built on Microsoft Phi-3.5-mini-instruct. It goes through the full...
TalkT2-0.1b
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
small-like-claude-v2
Это точно настроенная модель LoRA / PEFT на основе unsloth/Qwen3.5-0.8B и openbmb/MiniCPM5-1B. Данные для обучения: mondk/claude-v2-super.jsonl Создано/собрано: mondk...
Supra2-100M-Instruct-ONNX
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Photon-1.0-1M
Welcome to Photon-1.0-1M, an ultra-compact, hyper-dense Small Language Model (SLM) developed by AtomixLabs. Built to explore performance efficiency...
Dillionv2-1.3M
Dillionv2 is our second generation model of the Dillion SLM family. It is a significant improvement over v1...
Supra-Mini-v3-0.5M
Supra Mini v3 0.5M is a very tiny base model trained on 1 billion tokens of Fineweb-Edu for...
htmLLM-124M
With this LLM, we wanted to see, how well tiny LLMs with just 124 million parameters can perform...