TroyDoesAI/Llama-3.1-8B-Instruct

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jul 23, 2024License:wtfplArchitecture:Transformer0.0K Cold

TroyDoesAI/Llama-3.1-8B-Instruct is an 8 billion parameter Llama-3.1-based instruction-tuned language model, developed by TroyDoesAI, featuring a 32768 token context length. This model is specifically configured to resolve a `rope_scaling` ValueError encountered when running the original Meta Llama 3.1 models, making it suitable for environments where this configuration fix is necessary.

Loading preview...

TroyDoesAI/Llama-3.1-8B-Instruct Overview

This model, developed by TroyDoesAI, is an 8 billion parameter instruction-tuned variant based on the Llama-3.1 architecture, featuring an extended context length of 32768 tokens. Its primary distinction lies in a critical configuration fix for the rope_scaling parameter, which addresses a common ValueError encountered when attempting to run the original Meta Llama 3.1 models in certain environments.

Key Capabilities

  • Llama-3.1 Foundation: Leverages the advanced capabilities and performance of the Llama-3.1 base model.
  • Extended Context: Supports a substantial 32768 token context window, enabling processing of longer inputs and generating more coherent, extended outputs.
  • Instruction-Tuned: Optimized for following instructions and performing various natural language tasks effectively.
  • Configuration Fix: Specifically engineered to resolve the rope_scaling error, facilitating smoother deployment and operation where this issue is prevalent.

Good For

  • Users experiencing rope_scaling configuration errors with original Meta Llama 3.1 models.
  • Applications requiring a robust 8B parameter instruction-tuned model with a large context window.
  • Developers seeking a Llama-3.1 variant that is pre-configured to avoid specific deployment hurdles related to rope_scaling.

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