license, base_model, library_name, pipeline_tag, tags
license base_model library_name pipeline_tag tags
llama3.1 meta-llama/Llama-3.1-8B-Instruct transformers text-generation
smat
model-merging

Llama-3.1-8B-Instruct · FT · ScienceQA

A FT expert from Table 1 of SMAT: Simple and Efficient Merge-Aware Training (training seed 42). SMAT trains experts that retain task performance while improving model merging.

Paper · GitHub & usage

Built with Llama. The included Llama 3.1 license and acceptable-use policy apply.

S
Description
Model synced from source: yanggangu/Llama-3.1-8B-Instruct-FT-ScienceQA
Readme
16 MiB
0 Stars 1 Watchers 0 Forks
Languages
Jinja 100%