HF model

llm-jp / llm-jp-4.1-8b-thinking-gguf

LLM‑jp‑4.1‑8b‑thinking is a 33 B transformer language model from the National Institute of Informatics, pre‑trained and mid‑trained without reinforcement learning, aligned via SFT and DPO, available for use with llama.cpp (fork required) and detailed in the provided cookbook.

Description in other languages

Statistics

Statistics as of Nov 16, 2026

Hugging Face downloads (last 30 days)
5,000
Hugging Face likes
16
Listed
Oct 5, 2026

Popular in the same category

Resources in similar research fields

Learn from slides & articles