Vigostral-7b-Chat-GGUF
Lien du modèle original: https://huggingface.co/bofenghuang/vigostral-7b-chat/ Le projet llama.cpp (pour l’inférence): https://github.com/ggerganov/llama.cpp/ Les modèles ont dans leur nom un...
Lien du modèle original: https://huggingface.co/bofenghuang/vigostral-7b-chat/ Le projet llama.cpp (pour l’inférence): https://github.com/ggerganov/llama.cpp/ Les modèles ont dans leur nom un...
> ⚠️ Preliminary results — 1 seed, variance not controlled. Every number below is a single training run...
Эта 24 ГБ VRAM-совместимая квантованная модель, предназначенная для работы с llama.cpp на 24 ГБ VRAM, представляет собой полностью...
> [!TIP] > This is avery small model, so it might not perform well for some prompts and...
> [!TIP] > This is avery small model, so it might not perform well for some prompts and...
 Это квантованная версия jpacifico/Chocolatine-3B-Instruct-DPO-Revised, созданная с использованием llama.cpp DPO, точно настроенная на microsoft/Phi-3-mini-4k-instruct (3.82B params) с использованием...
This is a French DPO fine-tune of Microsoft’s Phi-3-mini-4k-instruct, improving its global understanding performances, even in English. Fine-tuned...
French-Alpaca based on microsoft/Phi-3-mini-128k-instruct 128k is the context length (in tokens) fine-tuned from the original French-Alpaca-dataset entirely generated...
The MoE architecture of Magiq 3 combines the specialized capabilities of MAGIQ Core-0, MAGIQ Translator-0, and MAGIQ Logic-0...
The growing need of artificial intelligence tools around the world has created a run for GPU power. We...