bartowski/internlm2-chat-7b-sft-llama

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jan 18, 2024License:otherArchitecture:Transformer Featherless Exclusive Cold

The bartowski/internlm2-chat-7b-sft-llama model is an 8 billion parameter instruction-tuned causal language model, converted from the InternLM2-Chat-7B-SFT architecture. Developed by InternLM and converted by Charles Goddard, this model is designed for chat-based applications and general language tasks, offering an 8192-token context length. It provides a Llama-compatible implementation of the InternLM2-Chat-7B-SFT model, making it accessible for environments supporting the Llama architecture.

Loading preview...

Overview

This model, bartowski/internlm2-chat-7b-sft-llama, is an 8 billion parameter instruction-tuned language model. It is a conversion of the original InternLM2-Chat-7B-SFT model, adapted to be compatible with the Llama architecture using a conversion script by Charles Goddard. The model supports a context length of 8192 tokens.

Key Capabilities

  • Chat-based interactions: Optimized for conversational AI and instruction following.
  • General language tasks: Suitable for a wide range of natural language processing applications.
  • Llama compatibility: Allows for deployment and use within ecosystems designed for Llama models.

Good For

  • Developers seeking a Llama-compatible version of the InternLM2-Chat-7B-SFT model.
  • Applications requiring an 8 billion parameter model for chat and instruction-following tasks.
  • Environments where the Llama architecture is preferred or already integrated.

Finetunes
2 models