Edit model card

Yi-1.5-9B-Chat-GGUF

Original Model

Prompt template:

prompt template: chatml

Reverse prompt

reverse prompt: <|im_end|>

Context size:

chat_ctx_size: 4096

Run with GaiaNet:

Quantized with llama.cpp b3135

GGUF

Model size

8.83B params

Architecture

llama

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

Quantized

(20)

this model