Hugging Face's logo

LM-Parallel
/
grpo_llama-hs-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250318005512_global_step_100

Safetensors
llama
Model card Files Community
grpo_llama-hs-v3_bs64_rollout5-lr1e-5-seq-weighted-kl0.01-20250318005512_global_step_100 / tokenizer.json
longlian's picture
longlian
Upload folder using huggingface_hub
a1f9881 verified
raw
history contribute delete
3.62 MB
File too large to display, you can check the raw version instead.