main
Model: yanggangu/Llama-3.1-8B-Instruct-FT-ScienceQA Source: Original Platform
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 |
|
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.
Built with Llama. The included Llama 3.1 license and acceptable-use policy apply.
Description
Model synced from source: yanggangu/Llama-3.1-8B-Instruct-FT-ScienceQA
16 MiB
0 Stars
1 Watchers
0 Forks
Languages
Jinja
100%