Downloads · 30 days
11
6% of all-time downloads
taesunwhang/vicuna-metamath-llemma-13b
vicuna-metamath-llemma-13b is a text generation model from taesunwhang. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama2.
Model merge based on lmsys/vicuna-7b-v1.5 and meta-math/MetaMath-Llemma-7B
Downloads · 30 days
11
6% of all-time downloads
All-time downloads
180
Public
Parameters
13.2B
39.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors26.4 GB · 100%
From the Hugging Face model README
Model merge based on lmsys/vicuna-7b-v1.5 and meta-math/MetaMath-Llemma-7B
Vicuna
Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
MetaMath Llemma
MetaMath-Llemma-7B is fully fine-tuned on the MetaMathQA datasets and based on the powerful Llemma-7B model. It is glad to see using MetaMathQA datasets and change the base model from llama-2-7B to Llemma-7B can boost the MATH performance from 19.8 to 30.0.