eren23/dpo-binarized-NeuralTrix-7B

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Feb 11, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The eren23/dpo-binarized-NeuralTrix-7B is a 7 billion parameter language model, fine-tuned using Direct Preference Optimization (DPO) on the argilla/OpenHermes2.5-dpo-binarized-alpha dataset. This model is based on the CultriX/NeuralTrix-7B-dpo architecture and is optimized for general language understanding and generation tasks. It demonstrates competitive performance across various benchmarks, making it suitable for applications requiring robust conversational AI and text completion.

Loading preview...

Overview

eren23/dpo-binarized-NeuralTrix-7B is a 7 billion parameter language model developed by eren23. It leverages the CultriX/NeuralTrix-7B-dpo architecture and has been fine-tuned using Direct Preference Optimization (DPO). The training utilized the argilla/OpenHermes2.5-dpo-binarized-alpha dataset, which is derived from teknium/OpenHermes-2.5 and processed with argilla-io/distilabel.

Key Capabilities & Performance

This model demonstrates strong performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard. Its average score is 76.17, indicating solid general-purpose capabilities. Specific benchmark results include:

  • AI2 Reasoning Challenge (25-Shot): 72.35
  • HellaSwag (10-Shot): 88.89
  • MMLU (5-Shot): 64.09
  • TruthfulQA (0-shot): 79.07
  • Winogrande (5-shot): 84.61
  • GSM8k (5-shot): 68.01

Good For

  • General text generation and understanding tasks.
  • Applications requiring a model with a balanced performance across reasoning, common sense, and language comprehension.
  • Use cases where a 7B parameter model offers a good balance between performance and computational efficiency.

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