!https://64.media.tumblr.com/1ab2cfe03429ef47b5063c90df2c0a5a/3c1a235d6f992b74-7d/s500x750/aafa42b7949f3104f349e5508df5fa8b738d879a.gif This repo contains a 4-bit precision version of artindnr/tea, a full fine-tune of microsoft/phi-4` for question answering and long, multi-turn assistant conversations, with fine-tuning focused on Farsi (Persian) conversational ability. Unlike GGUF quants, this is a safetensors checkpoint quantized to 4-bit precision with Unsloth (bitsandbytes nf4 backend), meant to be loaded directly with 🤗 Transformers or Unsloth — not with llama.cpp. > Looking for GGUF quants for llama.cpp / Ollama / LM Studio instead? See artindnr/tea-gguf (F16, Q80, Q5KM, Q4K_M). — Base model: artindnr/tea (full fine-tune of microsoft/phi-4, 14B parameters) — Quantized by: artindnr, using Unsloth — Format: safetensors (4-bit, bitsandbytes nf4) — License: MIT — Languages: Farsi (primary conversational focus), English, and general multilingual support The checkpoint is already stored in 4-bit, so it loads directly — no BitsAndBytesConfig needed on your end, devicemap=»auto»` handles placement. Unsloth also lets you use this checkpoint as a starting point for further QLoRA…
Модальности:
Генерация текста
Области применения:
Диалог / чат Мультиязычность Ответы на вопросы
Задача: Генерация текста
Автор: artindnr
Теги: llama, fine-tuned, full-fine-tune, 4-bit, bitsandbytes, unsloth, chat, question-answering
Лайков: 3 | Загрузок: 7
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
