krevas/LDCC-Instruct-Llama-2-ko-13B-v4
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kLicense:cc-by-nc-4.0Architecture:Transformer Open Weights Cold

krevas/LDCC-Instruct-Llama-2-ko-13B-v4 is a 13 billion parameter instruction-tuned causal language model developed by Lotte Data Communication, based on Meta's Llama 2 architecture. This model is fine-tuned for instruction following, leveraging DeepSpeed and HuggingFace libraries. It is designed for general natural language generation tasks, with a focus on assistant-like chat applications, and has a context length of 4096 tokens.

Loading preview...