m3rg-iitd/llamat-2-chat
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 3, 2024License:llama2Architecture:Transformer Open Weights Cold

LLaMat-2-Chat is a 7 billion parameter large language model developed by M3RG, IIT Delhi & DAIR, IIT Delhi, fine-tuned from LLaMat-2. It is specialized as an AI copilot for materials research, excelling at information extraction from material science texts and tabular data. The model is optimized for domain-specific instruction following and scientific data processing, with a context length of 4096 tokens. Its primary use case is assisting researchers in analyzing and interpreting material science literature, reports, and datasets.

Loading preview...