Downloads · 30 days
5
14% of all-time downloads
Qwen3_8B_no_thinking_sft_dpo
tinyrolls/Qwen3_8B_no_thinking_sft_dpo
Qwen3_8B_no_thinking_sft_dpo is a machine learning model from tinyrolls. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Checkpoint from the RoleVerse project — a multilingual benchmark for social reasoning through same-universe role-playing across 5 languages (EN, ZH, JA, FR, ES).
All-time downloads
36
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- May 12, 2026
- Updated
- May 12, 2026
- SHA
- eeb8868c
Datasets
Model card
From the Hugging Face model README
Qwen3_8B_no_thinking_sft_dpo
Checkpoint from the RoleVerse project — a multilingual benchmark for social reasoning through same-universe role-playing across 5 languages (EN, ZH, JA, FR, ES).
This checkpoint was produced by the RoleVerse training pipeline (SFT and/or DPO). See the project repo and dataset for details on how it was trained.
- Dataset: https://huggingface.co/datasets/tinyrolls/RoleVerse
- Repo ID:
tinyrolls/Qwen3_8B_no_thinking_sft_dpo
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "tinyrolls/Qwen3_8B_no_thinking_sft_dpo"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, zh, ja, fr, es
- Created
- May 12, 2026
- Updated
- May 12, 2026