metadata
license: apache-2.0
inference: false
BLING-QWEN-MINI-TOOL (1.5B)
bling-qwen-mini-tool is a RAG-finetuned version on Qwen2-1.5B for use in fact-based context question-answering, packaged with 4_K_M GGUF quantization, providing a very fast, very small inference implementation for use on CPUs.
To pull the model via API:
from huggingface_hub import snapshot_download
snapshot_download("llmware/bling-qwen-mini-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("bling-qwen-mini-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.
Model Description
- Developed by: llmware
- Model type: GGUF
- Language(s) (NLP): English
- License: Apache 2.0
Model Card Contact
Darren Oberst & llmware team