About

Microsoft's Phi-4 quant-finetuned on Telugu Instruction dataset. The resulting 4bit precision model's capabilities are:

  1. Telugu Langugage Fluency
  2. Math and Reasoning in Telugu
  3. STEM General Knowledge in Telugu

Uploaded model

  • Developed by: dumbequation
  • License: apache-2.0
  • Finetuned from model : unsloth/phi-4-unsloth-bnb-4bit
Downloads last month
1
Safetensors
Model size
8.48B params
Tensor type
BF16
·
F32
·
U8
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for dumbequation/Phi-4Garu-telugu-14b-q4

Base model

microsoft/phi-4
Finetuned
unsloth/phi-4
Quantized
(8)
this model

Dataset used to train dumbequation/Phi-4Garu-telugu-14b-q4

Collection including dumbequation/Phi-4Garu-telugu-14b-q4