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
merged
lora

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.

S
Description
Model synced from source: talzoomanzoo/qwen2_5_3b_uid_reference_lr3e6_step2
Readme
2 MiB
0 Stars 1 Watchers 0 Forks