adonlee/LLaMA_2_13B_SFT_v1

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The adonlee/LLaMA_2_13B_SFT_v1 is a 13 billion parameter Llama-2 based model with a 4096 token context length. It features general capability upgrades, enhancing multilingual ability, overall knowledge, extended communication, and technical skills through open-source data. This model is primarily recommended as an improved baseline for further fine-tuning rather than direct production deployment.

Loading preview...

Model Overview

adonlee/LLaMA_2_13B_SFT_v1 is a 13 billion parameter language model built upon the Llama-2 architecture, featuring a 4096 token context window. This version represents a general capability upgrade, leveraging open-source data to enhance several key areas.

Key Capabilities

  • Multilingual Ability: Improved understanding and generation across multiple languages.
  • Enhanced Knowledge: Broader general knowledge base compared to its Llama-2 predecessor.
  • Extended Communication: Better capabilities for sustained and coherent dialogue.
  • Technical Skill: Improved proficiency in technical tasks and understanding.

Recommended Use

This model is primarily intended as a superior baseline for additional fine-tuning. It offers an upgraded foundation over the standard Llama-2-13B for developers looking to build specialized applications. It is not recommended for direct deployment to production as a chat model without further fine-tuning, and users are responsible for its outputs.

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