Edit model card

Uploaded model

  • Developed by: saksornr
  • License: apache-2.0
  • Finetuned from model : SeaLLMs/SeaLLM-7B-v2.5

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

Downloads last month
217
Safetensors
Model size
4.78B params
Tensor type
F32
BF16
U8
Inference API
Input a message to start chatting with saksornr/SeaLLM-7B-v2.5-4bit.
Inference API (serverless) does not yet support transformers accelerate bitsandbytes models for this pipeline type.

Quantized from