I have converted the thing in GPTQ-v2
Group size 128 for one
Act order for another
and neither for a third
Let's see how many I upload.
Also converted to GGML in the GGML folder. Works on CPU.
- Downloads last month
- 37
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.