GitHub / haturusinghe / subasa-llm
A task-specific fine-tuning framework for large language models (Llama, Mistral etc.) focused on offensive language detection in multilingual contexts, with evaluation on the SOLD benchmark.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/haturusinghe%2Fsubasa-llm
PURL: pkg:github/haturusinghe/subasa-llm
Stars: 0
Forks: 0
Open issues: 0
License: mit
Language: Python
Size: 3.1 MB
Dependencies parsed at: Pending
Created at: 6 months ago
Updated at: 6 months ago
Pushed at: 6 months ago
Last synced at: 4 months ago
Topics: finetuning-llms, large-language-models, llama3, mistral, nlp