| --- |
| language: |
| - en |
| - zh |
| - ja |
| - fr |
| - es |
| license: apache-2.0 |
| tags: |
| - role-playing |
| - dialogue |
| - multilingual |
| - dpo |
| - sft |
| datasets: |
| - tinyrolls/RoleVerse |
| --- |
| |
| # Qwen3_8B_20260509_144913 |
| |
| 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_20260509_144913` |
|
|
| ## Usage |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_id = "tinyrolls/Qwen3_8B_20260509_144913" |
| tok = AutoTokenizer.from_pretrained(model_id) |
| model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto") |
| ``` |
|
|
