llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05

GRPO checkpoints exported by verl.

Every global_step_<N>/ folder is a complete bfloat16 Hugging Face model, uploaded as soon as the trainer finished writing that step.

from transformers import AutoModelForCausalLM, AutoTokenizer

step = "global_step_91"
model = AutoModelForCausalLM.from_pretrained("just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05", subfolder=step)
tokenizer = AutoTokenizer.from_pretrained("just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05", subfolder=step)
  • Base model: allenai/Llama-3.1-Tulu-3-8B-DPO
  • Run name: llama31_tulu3_8b_dpo_grpo_nonthink_constraint_only_b1024_c1_kl0p05
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for just1nseo/llama31-tulu3-8b-dpo-if-rlvr-constraint-only-kl0p05

Finetuned
(13)
this model