Downloads · 30 days
7
14% of all-time downloads
CL-From-Nothing/grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8
grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8 is a text generation model from CL-From-Nothing. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
GRPO (RLVE) fine-tune of Qwen3-1.7B on the POPE task, trained with verl.
Downloads · 30 days
7
14% of all-time downloads
All-time downloads
49
Public
Parameters
1.7B
3.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.4 GB · 100%
From the Hugging Face model README
GRPO (RLVE) fine-tune of Qwen3-1.7B on the POPE task, trained with verl.
global_step_112 (epoch 0)model_world_size_4) to HuggingFace format.from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
m = AutoModelForCausalLM.from_pretrained("CL-From-Nothing/grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8", dtype=torch.bfloat16)
tok = AutoTokenizer.from_pretrained("CL-From-Nothing/grpo_pope_rlve_qwen3-1.7b_step_112_resp16384-T1.0-n8")