Laibh/sft_meta-llama-Llama-3.18B

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 6, 2026Architecture:Transformer Featherless Exclusive Cold

Laibh/sft_meta-llama-Llama-3.18B is an 8 billion parameter language model, likely based on the Llama 3 architecture, developed by Laibh. This model is a fine-tuned version, indicated by 'sft' (supervised fine-tuning), suggesting optimization for specific tasks or improved instruction following. With an 8192-token context length, it is suitable for applications requiring processing moderately long inputs and generating coherent responses.

Loading preview...

Model Overview

This is a Hugging Face Transformers model, Laibh/sft_meta-llama-Llama-3.18B, which is an 8 billion parameter language model. The 'sft' in its name indicates that it has undergone supervised fine-tuning, suggesting it has been optimized for specific tasks or to follow instructions more effectively than its base model. It is likely derived from the Llama 3 architecture, given the 'meta-llama-Llama-3' in its identifier.

Key Characteristics

  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports an 8192-token context window, enabling it to handle and generate moderately long sequences of text.
  • Fine-tuned: The 'sft' designation implies it has been fine-tuned, likely for improved instruction following or specific downstream applications.

Potential Use Cases

Given its fine-tuned nature and 8 billion parameters, this model could be suitable for:

  • General text generation and completion tasks.
  • Instruction-following applications where specific outputs are desired.
  • Summarization and question-answering on moderately sized documents.
  • Applications requiring a balance of performance and resource usage.