devshaheen/Llama-2-7b-chat-finetune
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Nov 9, 2024License:mitArchitecture:Transformer Open Weights Cold

The devshaheen/Llama-2-7b-chat-finetune model is a 7 billion parameter instruction-following language model, fine-tuned by devshaheen from the NousResearch/Llama-2-7b-chat-hf base. Optimized for efficient text generation, question answering, and summarization, it leverages LoRA and 4-bit quantization for memory efficiency. This model is specifically trained on the mlabonne/guanaco-llama2-1k dataset to enhance its instruction-following capabilities.

Loading preview...