sknorr/StockSightTwo
TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 22, 2024License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
StockSightTwo is an 8 billion parameter Llama-3 based causal language model developed by sknorr, fine-tuned from unsloth/llama-3-8b-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general language tasks, leveraging its Llama-3 architecture for broad applicability.
Loading preview...
Model Overview
StockSightTwo is an 8 billion parameter language model developed by sknorr, based on the Llama-3 architecture. It was fine-tuned from the unsloth/llama-3-8b-bnb-4bit model, indicating an optimization for efficient training and deployment.
Key Characteristics
- Base Model: Llama-3-8B, providing a strong foundation for various NLP tasks.
- Training Efficiency: The model was trained 2x faster by utilizing Unsloth and Huggingface's TRL library, which suggests a focus on practical and resource-efficient development.
- License: Released under the Apache-2.0 license, allowing for broad use and distribution.
Potential Use Cases
- General Text Generation: Suitable for a wide range of text generation tasks due to its Llama-3 base.
- Research and Development: Its efficient training methodology makes it a good candidate for further experimentation and fine-tuning on specific datasets.
- Applications requiring a compact yet capable model: The 8B parameter count offers a balance between performance and computational requirements.