llmware/bling-stablelm-3b-gguf

Model Card for Model ID

bling-stablelm-3b-gguf is a quantized version of BLING Stable-LM 3B, with 4_K_M GGUF quantization, providing a fast, small inference implementation for use on CPUs.

bling-stablelm-3b 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/bling-stablelm-3b-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("llmware/bling-stablelm-3b-gguf")            
response = model.inference(query, add_context=text_sample, add_prompt_engineering="default_with_context")  

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: CC-BY-SA-4.0
• Quantized from model: llmware/bling-stablelm-3b

Model Card Contact

Darren Oberst & llmware team