Downloads · 30 days
5
3% of all-time downloads
disha20041005/adaanchor-qwen2.5-1.5b-lora-math-k2
adaanchor-qwen2.5-1.5b-lora-math-k2 is a machine learning model from disha20041005. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
This repo contains: - LoRA adapter weights (adaptermodel.bin) - Tokenizer files - adaanchoraux.pt (anchors + projection + layernorm for latent refinement)
Downloads · 30 days
5
3% of all-time downloads
All-time downloads
156
Public
Repo size
94.9 MB
Likes
0
Public
Click a slice to open those files.
.bin74 MB · 78%
From the Hugging Face model README
This repo contains:
adapter_model.bin)adaanchor_aux.pt (anchors + projection + layernorm for latent refinement)Base model: Qwen/Qwen2.5-1.5B-Instruct
K latent steps: 2, M anchors: 8
See the snippet in the notebook / chat for loading with PEFT + aux.