DRAGON Models
Collection
Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ..." the leading foundation base models
•
23 items
•
Updated
•
44
dragon-llama-answer-tool is a quantized version of DRAGON Llama 7B, with 4_K_M GGUF quantization, providing a fast, small inference implementation for use on CPUs.
dragon-llama-7b is a fact-based question-answering model, optimized for complex business documents.
To pull the model via API:
from huggingface_hub import snapshot_download
snapshot_download("llmware/dragon-llama-answer-tool", local_dir="/path/on/your/machine/", local_dir_use_symlinks=False)
Load in your favorite GGUF inference engine, or try with llmware as follows:
from llmware.models import ModelCatalog
model = ModelCatalog().load_model("dragon-llama-answer-tool")
response = model.inference(query, add_context=text_sample)
Note: please review config.json in the repository for prompt wrapping information, details on the model, and full test set.
Darren Oberst & llmware team