hwkwon/S-SOLAR-10.7B-v1.5

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:10.7BQuant:FP8Ctx Length:4kLicense:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Warm

hwkwon/S-SOLAR-10.7B-v1.5 is a 10.7 billion parameter language model developed by hwkwon, fine-tuned from chihoonlee10/T3Q-ko-solar-dpo-v5.0 using DeepSpeed. This model is trained on a dataset including translated public data and generated data, totaling approximately 110K entries. It is designed for general language generation tasks, leveraging its fine-tuned architecture for improved performance.

Loading preview...

Model Overview

hwkwon/S-SOLAR-10.7B-v1.5 is a 10.7 billion parameter language model, representing a fine-tuned iteration of the chihoonlee10/T3Q-ko-solar-dpo-v5.0 base model. The fine-tuning process utilized DeepSpeed, a deep learning optimization library, to enhance its capabilities.

Training Data

The model was trained on a proprietary dataset comprising approximately 110,000 entries. This dataset includes a combination of translated public data and internally generated data, contributing to its specific performance characteristics. Further details regarding the dataset composition are pending.

Prompt Format

Users should interact with the model using a specific prompt template:

### User: User query input

### Assistant:

Licensing

This model is distributed under the CC BY-NC 4.0 license. This license permits sharing and adaptation of the model for non-commercial purposes only, requiring attribution to the original creator.

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