Weyaxi/Samantha-Nebula-7B

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Oct 5, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Samantha-Nebula-7B is a 7 billion parameter language model developed by Weyaxi, created by merging ehartford/samantha-mistral-7b and PulsarAI/Nebula-7B. This model demonstrates a balanced performance across various benchmarks, achieving an average score of 52.87 on the Open LLM Leaderboard. It is suitable for general-purpose language tasks, with notable scores in HellaSwag and Winogrande.

Loading preview...

Samantha-Nebula-7B Overview

Samantha-Nebula-7B is a 7 billion parameter language model developed by Weyaxi. It is a merge of two distinct models: ehartford/samantha-mistral-7b and PulsarAI/Nebula-7B. This merging approach aims to combine the strengths of its constituent models to offer a versatile language processing capability.

Key Capabilities & Performance

The model's performance has been evaluated on the Open LLM Leaderboard, showcasing a balanced aptitude across several benchmarks:

  • Average Score: 52.87
  • HellaSwag (10-shot): 82.25
  • Winogrande (5-shot): 73.09
  • ARC (25-shot): 57.0
  • MMLU (5-shot): 54.21
  • TruthfulQA (0-shot): 49.58
  • DROP (3-shot): 42.57
  • GSM8K (5-shot): 11.37

These scores indicate its proficiency in common sense reasoning, reading comprehension, and general knowledge tasks, while showing areas for improvement in complex mathematical reasoning (GSM8K).

Good For

  • General text generation and understanding tasks.
  • Applications requiring strong common sense and reading comprehension.
  • Use cases where a 7B parameter model with balanced performance is desired.

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