Hugging Face's logo

poedator
/
opt-125m-bnb-4bit

Text Generation
Transformers
PyTorch
Safetensors
opt
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
poedator commited on
Commit
b2a17e4
•
1 Parent(s): b1d4e22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -1,4 +1,6 @@
1
  facebook/OPT-125m quantized using bitsandbytes 4-bit NF4 quantization.
2
  All license matters are set based on the underlying facebook/OPT-125m model.
3
 
4
- This model is work in progress, use it for testing https://github.com/huggingface/transformers/pull/26037 pull request only.
 
 
 
1
  facebook/OPT-125m quantized using bitsandbytes 4-bit NF4 quantization.
2
  All license matters are set based on the underlying facebook/OPT-125m model.
3
 
4
+ This model is work in progress, use it for testing https://github.com/huggingface/transformers/pull/26037 pull request only.
5
+
6
+ known issue: safetensors deleted linked `"quant_map" / "nested_quant_map"` items.