TheTravellingEngineer/llama2-7b-hf-guanaco

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jul 25, 2023Architecture:Transformer0.0K Cold

TheTravellingEngineer/llama2-7b-hf-guanaco is a 7 billion parameter language model based on Meta's Llama-2 architecture. It was fine-tuned using Supervised Fine-Tuning (SFT) on the Guanaco dataset, enhancing its conversational capabilities. This model is designed for general-purpose English language tasks, particularly those benefiting from instruction-following and dialogue generation.

Loading preview...

Model Overview

TheTravellingEngineer/llama2-7b-hf-guanaco is a 7 billion parameter language model built upon Meta's Llama-2-7b-hf base model. It has undergone Supervised Fine-Tuning (SFT) using the timdettmers/openassistant-guanaco dataset, which is known for its high-quality conversational data. This fine-tuning process aims to improve the model's ability to follow instructions and engage in dialogue, similar to the original Guanaco model's prompt style.

Key Characteristics

  • Base Architecture: Meta Llama-2-7b-hf
  • Parameter Count: 7 billion
  • Fine-tuning Method: Supervised Fine-Tuning (SFT)
  • Training Data: Guanaco dataset (timdettmers/openassistant-guanaco)
  • Language: English (en)
  • Format: Merged fp16 model

Use Cases

This model is suitable for applications requiring:

  • Instruction Following: Responding to user prompts and commands effectively.
  • Dialogue Generation: Engaging in conversational exchanges.
  • General Text Generation: Creating coherent and contextually relevant English text.

Users should be aware that this model is subject to the usage restrictions and license of the original Llama-2 model.