main
Model: talzoomanzoo/qwen2_5_3b_uid_reference_lr3e6_step2 Source: Original Platform
base_model, library_name, pipeline_tag, license, license_name, license_link, tags
| base_model | library_name | pipeline_tag | license | license_name | license_link | tags | ||
|---|---|---|---|---|---|---|---|---|
| Qwen/Qwen2.5-3B | transformers | text-generation | other | qwen-research | https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE |
|
qwen2_5_3b_uid_reference_lr3e6_step2
Full model weights from the UID reference training run, with the step 2 LoRA actor merged into Qwen/Qwen2.5-3B.
- Training job: 3977891
- Global step: 2
- Learning rate: 3e-6
- LoRA rank: 32; alpha: 16
- Export dtype: bfloat16
Load directly with AutoModelForCausalLM.from_pretrained; no separate adapter is required.
Description
Model synced from source: talzoomanzoo/qwen2_5_3b_uid_reference_lr3e6_step2
2 MiB
0 Stars
1 Watchers
0 Forks