LLMs
Large language models for text generation and analysis
Models
Mistral 7B
A 7.3 billion parameter language model that performs well on reasoning, math, and coding tasks

DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek-R1-Distill-Qwen-1.5B is a 1.5 billion parameter language model that was created by distilling the larger Qwen model. The model has been optimized specifically for tasks that involve reasoning.
LLama 3.2 1B
A compact 1 billion parameter version of meta's llama 3.2 model, optimized for efficiency
