-
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
Mixtral of Experts
Paper • 2401.04088 • Published • 159 -
How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior
Paper • 2404.10198 • Published • 8 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50
Dragan Stoll
dragstoll
·
AI & ML interests
NLP, Prediction
Recent Activity
new activity
about 2 months ago
mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit:mlx-lm not ready
new activity
about 2 months ago
mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit:mlx-lm not ready
new activity
3 months ago
openai/gpt-oss-120b:poor multi language support
Organizations
-
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
Mixtral of Experts
Paper • 2401.04088 • Published • 159 -
How faithful are RAG models? Quantifying the tug-of-war between RAG and LLMs' internal prior
Paper • 2404.10198 • Published • 8 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50
datasets
0
None public yet