@abacaj
Releasing mistral-7b-sft, an initial fine-tune for code completion, explanation and repair. MMLU scores dropped from the base mistral model (as expected) but still much higher than codellama model and comparable to llama-2 7b HumanEval: pass@1 54.27% MMLU: 45.89% https://t.co/C4SfYepsOl