DeepSeek-R1-Flax-1.5B-Distill
Flax implementation of DeepSeek-R1 1.5B distilled reasoning LLM.
- from
- JAX
- added
- 2026-10-10
- likes
- 0
similar
-
-
Build a DeepSeek Model (From Scratch) manning.com
A book about implementing DeepSeek-style LLM architecture, training, and distillation methods.
-
LLMs Meet Finance arxiv.org
A three-stage fine-tuning pipeline (SFT → DPO → synthetic-data RL) that adapts Qwen2.5 and DeepSeek-R1 to financial tasks on the Open FinLLM Leaderboard, with findings on cross-task transfer and data scaling laws in finance.
-
-
Dreamfields github.com
Official implementation of the ICLR 2022 paper Progressive Distillation for Fast Sampling of Diffusion Models.
-
EasyLM github.com
LLMs made easy: Pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
JAX › Models and Projects > Flax: “Flax implementation of DeepSeek-R1 1.5B distilled reasoning LLM.”