lllqaq/R2EGym-7B-Agent-Coder-Instruct-checkpoint-800
012
R2EGym-7B-Agent-Coder-Instruct (checkpoint-800)
This repository contains a training checkpoint exported from LLaMA-Factory.
- Base:
Qwen/Qwen2.5-Coder-7B-Instruct - Training: SFT with DeepSpeed ZeRO-3
- Checkpoint:
checkpoint-800
Notes
- This repo includes ZeRO optimizer states in
global_step800/for resuming training. - For inference, use the
model-0000*-of-00004.safetensorsshards and tokenizer files.