Edit model card

codegemma-7b-it-ov

codegemma-7b-it-ov is an OpenVino int4 quantized version of Google's CodeGemma-7B with Instruct Training (IT), providing a fast inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.

codegemma-7b-it-ov is a leading open source coding model from Google.

Model Description

  • Developed by: Google
  • Quantized by: llmware
  • Model type: gemma-7b
  • Parameters: 7 billion
  • Model Parent: google/codegemma-7b-it
  • Language(s) (NLP): English
  • License: Gemma
  • Uses: Coding assistant with instruction chat support
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website

Downloads last month
19
Inference API
Inference API (serverless) has been turned off for this model.

Model tree for llmware/codegemma-7b-it-ov

Quantized
(8)
this model

Collection including llmware/codegemma-7b-it-ov