Pygmalion 7B (q4_0 ggml version)
Converted from the XORed weights from PygmalionAI (i.e. ready for use).
Additionally, converted from bfloat16 to float16.
Additionally, converted from float16 to ggml float16.
Additionally, quantized from ggml float16 to ggml q4_0.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model authors have turned it off explicitly.