Markr-AI/pub-llama-13b-v1

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Oct 19, 2023License:cc-by-nc-sa-4.0Architecture:Transformer Open Weights Cold

Markr-AI/pub-llama-13b-v1 is a 13 billion parameter auto-regressive language model developed by Kyujin Han as part of an LLM research consortium. Based on the LLaMA2 transformer architecture, it processes text input to generate text output. This model is trained on the HumanF-MarkrAI/pub_COT-2000 dataset, focusing on specific research applications.

Loading preview...

Model Overview

Markr-AI/pub-llama-13b-v1 is a 13 billion parameter auto-regressive language model developed by Kyujin Han, a key contributor to an LLM research consortium. It is built upon the robust LLaMA2 transformer architecture, designed to process text inputs and generate coherent text outputs.

Key Characteristics

  • Architecture: Utilizes the LLaMA2 transformer architecture, known for its strong performance in language understanding and generation tasks.
  • Developer: Developed by Kyujin Han, indicating a focused research effort within the consortium.
  • Training Data: Trained on the HumanF-MarkrAI/pub_COT-2000 dataset, suggesting a specialization in specific data patterns or domains relevant to this dataset.
  • Input/Output: Handles text-only inputs and produces text-only outputs.

Licensing

The model is released under the cc-by-nc-sa license, which permits non-commercial use with attribution and requires sharing alike for any adaptations.

Finetunes
1 models