standrey/listing-parser-llama31-8b-ft-v1
TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Apr 28, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The standrey/listing-parser-llama31-8b-ft-v1 is an 8 billion parameter Llama 3.1 model, fine-tuned by standrey from unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is specialized for parsing tasks, leveraging its Llama 3.1 architecture for efficient text processing.
Loading preview...
Model Overview
The standrey/listing-parser-llama31-8b-ft-v1 is an 8 billion parameter language model, fine-tuned by standrey. It is based on the Meta-Llama-3.1-8B-Instruct architecture, specifically the unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit version, and features a 32768 token context length.
Key Capabilities
- Specialized Parsing: This model is specifically fine-tuned for parsing tasks, indicating an optimization for extracting structured information from text.
- Efficient Training: The fine-tuning process utilized Unsloth and Huggingface's TRL library, which allowed for a 2x faster training speed compared to standard methods.
- Llama 3.1 Foundation: Benefits from the robust capabilities and performance of the Llama 3.1 instruction-tuned base model.
Good For
- Structured Data Extraction: Ideal for applications requiring the parsing of listings or other text-based data into a structured format.
- Developers seeking optimized Llama 3.1: Offers a fine-tuned Llama 3.1 variant with specific parsing capabilities, built on an efficient training framework.