llmware/dragon-qwen-7b-gguf

Model Card for Model ID

dragon-qwen-7b-gguf is a quantized version of a fact-based question answering model, optimized for complex business documents, fine-tuned on top of Qwen2 7B base, and then packaged with 4_K_M GGUF quantization, providing a fast, small inference implementation for use on CPUs.

Benchmark Tests

Evaluated against the benchmark test: RAG-Instruct-Benchmark-Tester
1 Test Run with sample=False & temperature=0.0 (deterministic output) - 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.

--Accuracy Score: 99.0 correct out of 100
--Not Found Classification: 85.0%
--Boolean: 100.0%
--Math/Logic: 92.5%
--Complex Questions (1-5): 5 (Best in Class)
--Summarization Quality (1-5): 3 (Average)
--Hallucinations: No hallucinations observed in test runs.

For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).

To pull the model via API:

from huggingface_hub import snapshot_download           
snapshot_download("llmware/dragon-qwen-7b-gguf", 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-qwen-7b-gguf")            
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.

Model Description

• Developed by: llmware
• Model type: GGUF
• Language(s) (NLP): English
• License: Apache 2.0
• Quantized from model: llmware/dragon-qwen

Model Card Contact

Darren Oberst & llmware team