MaziyarPanahi/Calme-7B-Instruct-v0.9

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Apr 2, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

MaziyarPanahi/Calme-7B-Instruct-v0.9 is a 7 billion parameter instruction-tuned language model, fine-tuned by MaziyarPanahi on high-quality datasets, building upon the Mistral-7B architecture. This model is designed to generate text with notable clarity, calmness, and coherence, making it suitable for applications requiring precise and well-structured responses. It supports a context length of 8192 tokens and is also available in various GGUF quantized formats for broader accessibility on commodity hardware.

Loading preview...

Model Overview

Calme-7B-Instruct-v0.9 is a 7 billion parameter instruction-tuned language model developed by MaziyarPanahi. It is built on the Mistral-7B architecture and has been fine-tuned using high-quality datasets to enhance its text generation capabilities. A key characteristic of this model is its ability to produce text that is clear, calm, and coherent, aiming for high-quality, well-structured outputs.

Key Capabilities

  • Instruction Following: Designed to respond effectively to user instructions.
  • Coherent Text Generation: Excels in generating text with clarity and logical flow.
  • Multilingual Support: Demonstrated with examples in French and Ukrainian, indicating potential for diverse language applications.
  • Accessibility: Available in various GGUF quantized formats (2-bit to 8-bit) to facilitate deployment on commodity hardware without specialized accelerators.

Good For

  • Applications requiring calm, clear, and coherent textual responses.
  • Instruction-based tasks where precise and well-structured output is critical.
  • Users looking for an accessible 7B model that can run on standard personal computers due to its GGUF quantization.

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