Skip to content

professorsynapse

eh-qwen3-4b-clean-sft-grpo-v2-seed1-lora

professorsynapse/eh-qwen3-4b-clean-sft-grpo-v2-seed1-lora

eh-qwen3-4b-clean-sft-grpo-v2-seed1-lora is a text generation model from professorsynapse. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.

A LoRA adapter for the reinforcement-learning stage of a response-confidence training track. The model is trained to emit an answer together with a numeric confidence in [0, 1], and this stage applies group-relative p…

Downloads · 30 days

11

24% of all-time downloads

All-time downloads

46

Public

Repo size

276 MB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors264 MB · 94%

At a glance

Task
Text Generation
Library
peft
License
apache-2.0
Access
Public
Created
Jul 5, 2026
Updated
Aug 1, 2026
SHA
0b0daa7f

Try a prompt

Base models

Task
Text Generation
Library
peft
License
apache-2.0
Created
Jul 5, 2026
Updated
Aug 1, 2026