Merge

[Inference] Remove simple mode and use OpenAI API (#220) #107

Job	Run time
Lint / lint	30s
Tests / docker-test (3.9)	17m 35s
Tests / getting-started-test (3.9)	3m 0s
Tests / docker-test (3.10)	17m 59s
Tests / getting-started-test (3.10)	2m 57s
Tests / docker-test (3.11)	17m 38s
Tests / getting-started-test (3.11)	2m 56s
Tests / setup-test (3.9)	2m 41s
Tests / bare-test (3.9)	16m 26s
Tests / setup-test (3.10)	2m 5s
Tests / bare-test (3.10)	16m 21s
Tests / setup-test (3.11)	2m 4s
Tests / bare-test (3.11)	15m 59s
Finetune / finetune (EleutherAI/gpt-j-6b)	22m 41s
Finetune / finetune (meta-llama/Llama-2-7b-chat-hf)	20m 41s
Inference / inference (gpt-j-6b)	13m 17s
Finetune / finetune (mistralai/Mistral-7B-v0.1)	24m 11s
Inference_Gaudi / inference (llama-2-7b-chat-hf)	1s
Inference / inference (mistral-7b-v0.1)	7m 38s
Finetune / finetune (google/gemma-2b)	7m 31s
Inference_Gaudi / inference (llama-2-70b-chat-hf)	18s
Inference / inference (mpt-7b-ipex-llm)	7m 6s
Inference / inference (llama-2-7b-chat-hf-vllm)	4m 57s
Inference / inference (gemma-2b)	6m 26s
Inference / inference (mpt-7b, nathan0/mpt-7b-deltatuner-model)	25m 23s
	4h 18m 21s

Provide feedback