weizechen
/

RL-Compositionality-Stage-1-Model

Model card Files Files and versions

The model after Stage 1 RFT.

Paper: https://huggingface.co/papers/2509.25123

Code: https://github.com/PRIME-RL/RL-Compositionality

Downloads last month: 23

Safetensors

Model size

8B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for weizechen/RL-Compositionality-Stage-1-Model

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(1865)

this model

Dataset used to train weizechen/RL-Compositionality-Stage-1-Model

Collection including weizechen/RL-Compositionality-Stage-1-Model

RL Compositionality

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones. https://huggingface.co/papers/2509.25123 • 5 items • Updated 12 days ago