glavin001
/
exllama-airoboros-7b-gpt4-1.4-gptq
Test out fast inference with ExLlama and 4bit quantization!
- Public
- 1.7K runs
-
- Author
- @glavin001
- Version
- 22.04
- Commit
- bce83b24e1d8074867435a5edaf5f0e349a1a92f
34318c92
Latest -
- Author
- @glavin001
- Version
- 22.04
- Commit
- bce83b24e1d8074867435a5edaf5f0e349a1a92f