FemkeBakker/AmsterdamDocClassificationLlama200T3Epochs
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jun 3, 2024License:llama2Architecture:Transformer Open Weights Cold

The FemkeBakker/AmsterdamDocClassificationLlama200T3Epochs is a 7 billion parameter Llama-2-7b-chat-hf model, fine-tuned by FemkeBakker for document classification. This model was specifically trained for three epochs on the AmsterdamBalancedFirst200Tokens dataset, which consists of documents truncated to their first 200 tokens. It is optimized for classifying short document excerpts, achieving a validation loss of 0.8116. This model is a specialized tool for document classification tasks within the context of the Municipality of Amsterdam's research.

Loading preview...