chaddy81/Meta-Llama-3.1-8B-Instruct-coder

TEXT GENERATIONPricing:Input $0.2 / Cached $0.028 / Output $0.32Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 9, 2025License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

chaddy81/Meta-Llama-3.1-8B-Instruct-coder is an 8 billion parameter instruction-tuned language model developed by chaddy81, finetuned from unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general instruction-following tasks, leveraging the Meta-Llama-3.1 architecture.

Loading preview...

Model Overview

chaddy81/Meta-Llama-3.1-8B-Instruct-coder is an 8 billion parameter instruction-tuned model, developed by chaddy81. It is finetuned from the unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit base model, indicating its foundation in the Meta-Llama-3.1 architecture.

Key Characteristics

  • Efficient Training: This model was trained significantly faster, achieving 2x speed improvements, by utilizing the Unsloth library in conjunction with Huggingface's TRL library.
  • Instruction-Tuned: As an instruction-tuned variant, it is optimized for understanding and executing a wide range of user prompts and instructions.
  • Parameter Count: With 8 billion parameters, it offers a balance between performance and computational efficiency.

Good For

  • General Instruction Following: Suitable for various tasks requiring the model to follow specific instructions.
  • Applications requiring efficient inference: Given its Unsloth-optimized training, it may be well-suited for scenarios where faster processing is beneficial.