Edit model card

Uploaded model

Pre-quantized for faster loading. (~17 GB to 5 GB)

Safetensors

Model size

4.78B params

Tensor type

F32

BF16

Inference Examples

Inference API (serverless) does not yet support transformers accelerate bitsandbytes models for this pipeline type.

Model tree for saksornr/SeaLLM-7B-v2.5-4bit

Base model

Quantized

(14)

this model

Finetunes