LLM: add star_corder_15.5b model (#9772)

* LLM: add star_corder_15.5b model

* revert llm_performance_tests.yml

python/llm/dev/benchmark/all-in-one/run.py

@@ -371,6 +371,10 @@ def run_transformer_int4_gpu(repo_id,
                                                      use_cache=True).eval()
         tokenizer = LlamaTokenizer.from_pretrained(model_path, trust_remote_code=True)
         model = model.to('xpu')
+    else:
+        if 'starcoder' in repo_id:
+            model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, load_in_low_bit=low_bit,
+                                                        trust_remote_code=True, use_cache=True, torch_dtype=torch.bfloat16).eval()
         else:
             model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, load_in_low_bit=low_bit,
                                                         trust_remote_code=True, use_cache=True).eval()

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

@@ -5,7 +5,7 @@ repo_id:
   - 'tiiuae/falcon-7b-instruct-with-patch'
   - 'mosaicml/mpt-7b-chat'
   - 'redpajama/gptneox-7b-redpajama-bf16'
-  # - 'bigcode/starcoder-15.5b'
+  - 'bigcode/starcoder-15.5b'
   - 'databricks/dolly-v1-6b'
   - 'databricks/dolly-v2-7b'
   - 'databricks/dolly-v2-12b'