Mcholo/llama-3-8b-chat-legal-unsloth

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Jun 24, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Mcholo/llama-3-8b-chat-legal-unsloth is an 8 billion parameter Llama-3 model developed by Mcholo, fine-tuned from unsloth/llama-3-8b-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for chat applications, likely with a focus on legal contexts given its name.

Loading preview...

Mcholo/llama-3-8b-chat-legal-unsloth Overview

This model, developed by Mcholo, is an 8 billion parameter Llama-3 variant fine-tuned from unsloth/llama-3-8b-bnb-4bit. It leverages the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x speedup in its training process.

Key Characteristics

  • Base Model: Llama-3 8B
  • Fine-tuning: Utilizes Unsloth and Huggingface TRL for efficient training.
  • Training Efficiency: Achieved 2x faster training compared to standard methods.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

Given its "legal" designation in the model name, this model is likely optimized for:

  • Legal Chatbots: Engaging in conversational AI within legal domains.
  • Legal Information Retrieval: Assisting with queries related to legal documents or concepts.
  • Legal Text Generation: Generating text relevant to legal contexts, such as summaries or drafts.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p