Hugging Face's logo

turboderp
/
gpt2-exl2

Model card Files Community
turboderp commited on
Commit
a2b7ce2
·
verified ·
1 Parent(s): d66f173

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,6 +7,6 @@ EXL2 quants of [GPT2](https://huggingface.co/openai-community/gpt2)
7
  [3.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/3.0bpw)
8
  [4.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/4.0bpw)
9
  [6.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/6.0bpw)
10
- [8.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/6.0bpw)
11
 
12
  [measurement.json](https://huggingface.co/turboderp/gpt2-exl2/blob/main/measurement.json)
 
7
  [3.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/3.0bpw)
8
  [4.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/4.0bpw)
9
  [6.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/6.0bpw)
10
+ [8.00 bits per weight](https://huggingface.co/turboderp/gpt2-exl2/tree/8.0bpw)
11
 
12
  [measurement.json](https://huggingface.co/turboderp/gpt2-exl2/blob/main/measurement.json)