Lajonbot/Llama-2-13b-hf-instruct-pl-lora_unload

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Jul 30, 2023License:otherArchitecture:Transformer0.0K Warm

Lajonbot/Llama-2-13b-hf-instruct-pl-lora_unload is a 13 billion parameter Llama-2 based instruction-tuned language model. It is specifically fine-tuned for text generation in Polish, leveraging a Polish-only instruction dataset. This model is designed for applications requiring high-quality, instruction-following text generation in the Polish language.

Loading preview...

Model Overview

Lajonbot/Llama-2-13b-hf-instruct-pl-lora_unload is a 13 billion parameter language model built upon the Llama-2 architecture. This model has undergone instruction-tuning specifically for the Polish language, utilizing the Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish dataset. Its primary focus is to provide robust text generation capabilities tailored for Polish-speaking users and applications.

Key Capabilities

  • Polish Language Generation: Optimized for understanding and generating text in Polish.
  • Instruction Following: Designed to respond to instructions effectively, a result of its instruction-tuning process.
  • Llama-2 Foundation: Benefits from the strong base capabilities of the Llama-2 13B model.

Good For

  • Polish-centric applications: Ideal for chatbots, content creation, or virtual assistants operating primarily in Polish.
  • Research and development: Useful for exploring instruction-tuned models in less-resourced languages.
  • Text generation tasks: Suitable for various tasks requiring coherent and contextually relevant Polish text output.

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