Downloads · 30 days
0
just1nseo/tulu3-8b-dpo-grpo-q30ba3b-t7
tulu3-8b-dpo-grpo-q30ba3b-t7 is a text generation model from just1nseo. Use it when you need the model to write or continue text. It is set up for transformers.
Downloads · 30 days
0
Access
Public
Updated Aug 22, 2026
Repo size
193 GB
Likes
0
Public
Click a slice to open those files.
.safetensors193 GB · 100%
From the Hugging Face model README
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_92"
model = AutoModelForCausalLM.from_pretrained("just1nseo/tulu3-8b-dpo-grpo-q30ba3b-t7", subfolder=step)
tokenizer = AutoTokenizer.from_pretrained("just1nseo/tulu3-8b-dpo-grpo-q30ba3b-t7", subfolder=step)
allenai/Llama-3.1-Tulu-3-8B-DPOllama31_tulu3_8b_dpo_grpo_nonthink_llmverifier_qwen3_30ba3b_nonthink_bonus01_threshold7_b1024_c1_t1_2k