Large Language Models and Multimodal AI
29 repos
Python-based tools, frameworks, and evaluation systems for building and extending large language models and multimodal AI systems. The cluster spans model implementations (LLaVA, Otter), academic research infrastructure (gpt_academic), evaluation frameworks (evalplus, evoeval), and agent orchestration systems (NExT-GPT). Core themes include prompt engineering, model fine-tuning, multimodal vision-language capabilities, and systematic evaluation of LLM outputs.
Python · 26
Go · 1
TypeScript · 1
chatgpt ·130,015
gpt-4 ·122,991
large-language-models ·85,971
chatglm-6b ·71,313
academic ·71,313
foundation-models ·40,226
multimodal ·37,085
instruction-tuning ·37,041
visual-language-learning ·35,527
llama ·35,414
