bongchoi/MoMo-70B-V1.1

TEXT GENERATIONConcurrency Cost:4Model Size:69BQuant:FP8Ctx Length:32kPublished:Nov 10, 2023License:llama2Architecture:Transformer Open Weights Cold

MoMo-70B-V1.1 is a 69 billion parameter language model developed by bongchoi, featuring a 32768-token context length. This model is fine-tuned using Orca-style and Alpaca-style datasets, focusing on instruction-following capabilities. It is designed for general-purpose conversational AI and task execution based on diverse instruction formats.

Loading preview...

MoMo-70B-V1.1 Overview

MoMo-70B-V1.1 is a 69 billion parameter language model developed by bongchoi, distinguished by its substantial 32768-token context window. This model has been specifically fine-tuned using a combination of Orca-style and Alpaca-style datasets, which are known for enhancing instruction-following and conversational abilities. The training methodology focused exclusively on these datasets, ensuring no overlap with benchmark test sets or other training data.

Key Capabilities

  • Instruction Following: Optimized for understanding and executing a wide range of instructions, leveraging both Orca-style and Alpaca-style data formats.
  • Extended Context: Benefits from a 32768-token context length, allowing for processing and generating longer, more coherent responses and handling complex, multi-turn conversations.
  • General-Purpose AI: Designed to be a versatile model suitable for various natural language processing tasks.

Good For

  • Applications requiring robust instruction adherence.
  • Scenarios benefiting from a large context window, such as detailed summarization or extended dialogue.
  • General conversational agents and task-oriented assistants.