MDL
DeepSeek-R1-Distill-Qwen-1.5B
litert-community
Parameters
1.5B
Downloads
97K
on HF
Likes
38
Avg score
—
Weights
Open
Released
Feb 14, 2025
About
DeepSeek-R1-Distill-Qwen-1.5B is a 1.5B-parameter open-weights model in the DeepSeek family from litert-community.
mittext-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →fg-expo: Frontier-guided exploration-prioritized policy optimization via adaptive kl and gaussian curriculumMay 12, 2026expo: Exploration-prioritized policy optimization via adaptive kl regulation and gaussian curriculum samplingMay 11, 2026Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency AwarenessMay 10, 2026Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal StatesMay 8, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Details
Publisherlitert-community
FamilyDeepSeek
Parameters1.5B
Licensemit
WeightsOpen
ReleasedFeb 14, 2025