LLM: add remaining models to the arc perf test (#9384)

* add remaining models

* modify the filepath which stores the test result on ftp server

* resolve some comments

.github/workflows/llm_performance_tests.yml

@@ -108,7 +108,6 @@ jobs:
           python -m pip install --upgrade einops
           python -m pip install --upgrade transformers_stream_generator
           python -m pip install --upgrade tiktoken
-          python -m pip install transformers==4.34.0
 
       - name: Download llm binary
         uses: ./.github/actions/llm/download-llm-binary
@@ -132,12 +131,12 @@ jobs:
           export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
           mv python/llm/test/benchmark/arc-perf-test.yaml python/llm/dev/benchmark/all-in-one/config.yaml
           cd python/llm/dev/benchmark/all-in-one
-          export http_proxy=${HTTP_PROXY}
-          export https_proxy=${HTTPS_PROXY}
           python run.py
           cp ./*.csv /mnt/disk1/nightly_perf_gpu/
           cd ../../../test/benchmark
           python csv_to_html.py -f /mnt/disk1/nightly_perf_gpu/
+          cd ../../dev/benchmark/all-in-one/
+          curl -T ./*.csv ${LLM_FTP_URL}/llm/nightly_perf/gpu/
 
           
   llm-performance-test-on-spr:

python/llm/test/benchmark/arc-perf-test.yaml

@@ -4,7 +4,6 @@ repo_id:
   - 'THUDM/chatglm2-6b'
   - 'tiiuae/falcon-7b-instruct-with-patch'
   - 'mosaicml/mpt-7b-chat'
-  # - 'bigscience/bloomz-7b1' # temporarily removed
   - 'redpajama/gptneox-7b-redpajama-bf16'
   - 'bigcode/starcoder-15.5b'
   - 'databricks/dolly-v1-6b'
@@ -16,7 +15,8 @@ repo_id:
   - 'Qwen/Qwen-7B-Chat-10-12'
   - 'BAAI/AquilaChat-7B'
   - 'baichuan-inc/Baichuan2-7B-Chat'
-  # - 'mistralai/Mistral-7B-v0.1' # temporarily removed
+  # - 'mistralai/Mistral-7B-v0.1'
+  - 'bigscience/bloomz-7b1'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3