Edit model card

Gemma-2-27b-it-GGUF

Original Model

Prompt template:

prompt template: gemma-instruct

Context size:

chat_ctx_size: 8192

Run with GaiaNet

Quantized with llama.cpp b3259

GGUF

Model size

27.2B params

Architecture

gemma2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples

Inference API (serverless) has been turned off for this model.

Base model

Finetuned

Quantized

(40)

this model