A RL-trained version of the R1-version of Qwen2.5 14B. They use the insights from DAPO for an improved version of GRPO, which we covered here.
Specs
Params14B
LicenseMIT
Tags
modelsmodels/llmsmodels/llms/reasoningartifacts/9
RAM score
—
Hugging Face Downloads
284
last 30d
150.1K
all time
HF Likes
679
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
0012:001b:0024:003e:0091:0110:03b3:5dc2
Explore other models with behavioral similarity to DeepCoder-14B-Preview.
Related Models
