Edit model card

A quantized version of Shinoji Research's Senku 70B Full. Quantized through AWQ:

Quantization settings:

{"zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
Downloads last month
1
Safetensors
Model size
9.68B params
Tensor type
I32
·
FP16
·
Inference API
Input a message to start chatting with bigquant/Senku-70B-AWQ-4bit-GEMM.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.