heavytail/kullm-solar-S

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:10.7BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer Open Weights Warm

The heavytail/kullm-solar-S model is a 10.7 billion parameter causal language model based on the Upstage/SOLAR-10.7B-Instruct-v1.0 architecture. Developed by heavytail, it has been fine-tuned using the KULLM dataset and hand-crafted instruction data. This model is designed for instruction-following tasks, leveraging its specialized training to enhance performance in conversational and generative AI applications.

Loading preview...

KULLM-SOLAR-S Overview

heavytail/kullm-solar-S is a 10.7 billion parameter instruction-tuned language model built upon the Upstage/SOLAR-10.7B-Instruct-v1.0 base model. This model distinguishes itself through its specialized fine-tuning process, which incorporates the KULLM dataset alongside custom, hand-crafted instruction data.

Key Capabilities

  • Instruction Following: Optimized for understanding and executing complex instructions, making it suitable for a wide range of interactive AI applications.
  • Generative Tasks: Leverages its base architecture and fine-tuning to produce coherent and contextually relevant text.
  • Efficient Deployment: Designed to be run with torch.float16 and device_map='auto', facilitating deployment on various hardware configurations.

Good For

  • Applications requiring robust instruction-following capabilities.
  • Developing conversational agents and chatbots.
  • Tasks benefiting from a model fine-tuned on diverse instruction datasets.

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