Spaces:
Running
Running
Locally deployed models have poor performance. model:CodeLlama-34b-Instruct-hf
#283
by
like123
- opened
When CodeLlama-34b-Instruct-hf was deployed with transformers and the default parameters were used for inference, it was found that the inference effect was very different from the hugging face, did the online inference do anything optimized? How are the model parameters and promot set?