Description

This model is a fine-tuned version of Microsoft's phi-3-medium-instruct (4k context), created using QLoRA on a 900k token private Chemical Engineering dataset on Unit Operations (topics including fluid mechanics revision, heat exchange, absorption, distillation, and adsorption). The GGUF model was converted using llama.cpp (on the HF Space 'gguf-my-repo'). Its intended use is for research and training.

Downloads last month
7
GGUF
Model size
14B params
Architecture
phi3
Hardware compatibility
Log In to view the estimation
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for zachaman/chpr3019-Q8_0-GGUF

Quantized
(2)
this model