File size: 357 Bytes
d418914 b2a17e4 |
1 2 3 4 5 6 |
facebook/OPT-125m quantized using bitsandbytes 4-bit NF4 quantization.
All license matters are set based on the underlying facebook/OPT-125m model.
This model is work in progress, use it for testing https://github.com/huggingface/transformers/pull/26037 pull request only.
known issue: safetensors deleted linked `"quant_map" / "nested_quant_map"` items. |