The allura-org/Mistral-Small-24b-Sertraline-0304 is a 24 billion parameter instruction-tuned model based on the Mistral Small 3 architecture. This model is specifically fine-tuned for instruction following, leveraging the v7-Tekken instruct template. It aims to provide a robust and "decent" performance for general AI assistant tasks, with a context length of 32768 tokens.
No reviews yet. Be the first to review!
Hugging Face