add all models

intel-analytics · Jun 5, 2024 · 14b9e97 · 14b9e97
1 parent ed5e0ce
commit 14b9e97
Show file tree

Hide file tree

Showing 4 changed files with 46 additions and 46 deletions.
diff --git a/python/llm/test/benchmark/arc-perf-test-batch2.yaml b/python/llm/test/benchmark/arc-perf-test-batch2.yaml
@@ -1,23 +1,23 @@
 repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
-  # - 'meta-llama/Llama-2-13b-chat-hf'
-  # - 'THUDM/chatglm2-6b'
-  # - 'THUDM/chatglm3-6b-4bit'
-  # - 'tiiuae/falcon-7b-instruct-with-patch'
-  # - 'mosaicml/mpt-7b-chat'
-  # - 'redpajama/gptneox-7b-redpajama-bf16'
-  # - 'bigcode/starcoder-15.5b-4bit'
-  # - 'databricks/dolly-v1-6b'
-  # - 'databricks/dolly-v2-7b'
-  # - 'databricks/dolly-v2-12b'
-  # - 'internlm/internlm-chat-7b'
-  # - 'Qwen/Qwen-7B-Chat'
-  # - 'BAAI/AquilaChat-7B'
-  # - 'baichuan-inc/Baichuan2-7B-Chat'
-  # - 'baichuan-inc/Baichuan2-13B-Chat-4bit'
-  # - 'bigscience/bloomz-7b1'
+  - 'meta-llama/Llama-2-13b-chat-hf'
+  - 'THUDM/chatglm2-6b'
+  - 'THUDM/chatglm3-6b-4bit'
+  - 'tiiuae/falcon-7b-instruct-with-patch'
+  - 'mosaicml/mpt-7b-chat'
+  - 'redpajama/gptneox-7b-redpajama-bf16'
+  - 'bigcode/starcoder-15.5b-4bit'
+  - 'databricks/dolly-v1-6b'
+  - 'databricks/dolly-v2-7b'
+  - 'databricks/dolly-v2-12b'
+  - 'internlm/internlm-chat-7b'
+  - 'Qwen/Qwen-7B-Chat'
+  - 'BAAI/AquilaChat-7B'
+  - 'baichuan-inc/Baichuan2-7B-Chat'
+  - 'baichuan-inc/Baichuan2-13B-Chat-4bit'
+  - 'bigscience/bloomz-7b1'
 #  - 'fnlp/moss-moon-003-sft-4bit' # moss-moon-003-sft cannot work on transformers 4.34+
-  # - 'mistralai/Mistral-7B-v0.1'
+  - 'mistralai/Mistral-7B-v0.1'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3
@@ -32,7 +32,7 @@ test_api:
   - "transformer_int4_gpu"  # on Intel GPU
 cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
 exclude:
-  # - 'bigcode/starcoder-15.5b-4bit:2048'
-  # - 'databricks/dolly-v2-12b:2048'
-  # - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
-  # - 'bigscience/bloomz-7b1:2048'
+  - 'bigcode/starcoder-15.5b-4bit:2048'
+  - 'databricks/dolly-v2-12b:2048'
+  - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
+  - 'bigscience/bloomz-7b1:2048'
diff --git a/python/llm/test/benchmark/arc-perf-test.yaml b/python/llm/test/benchmark/arc-perf-test.yaml
@@ -1,23 +1,23 @@
 repo_id:
   - 'meta-llama/Llama-2-7b-chat-hf'
-  # - 'meta-llama/Llama-2-13b-chat-hf'
-  # - 'THUDM/chatglm2-6b'
-  # - 'THUDM/chatglm3-6b-4bit'
-  # - 'tiiuae/falcon-7b-instruct-with-patch'
-  # - 'mosaicml/mpt-7b-chat'
-  # - 'redpajama/gptneox-7b-redpajama-bf16'
-  # - 'bigcode/starcoder-15.5b-4bit'
-  # - 'databricks/dolly-v1-6b'
-  # - 'databricks/dolly-v2-7b'
-  # - 'databricks/dolly-v2-12b'
-  # - 'internlm/internlm-chat-7b'
-  # - 'Qwen/Qwen-7B-Chat'
-  # - 'BAAI/AquilaChat-7B'
-  # - 'baichuan-inc/Baichuan2-7B-Chat'
-  # - 'baichuan-inc/Baichuan2-13B-Chat-4bit'
-  # - 'bigscience/bloomz-7b1'
+  - 'meta-llama/Llama-2-13b-chat-hf'
+  - 'THUDM/chatglm2-6b'
+  - 'THUDM/chatglm3-6b-4bit'
+  - 'tiiuae/falcon-7b-instruct-with-patch'
+  - 'mosaicml/mpt-7b-chat'
+  - 'redpajama/gptneox-7b-redpajama-bf16'
+  - 'bigcode/starcoder-15.5b-4bit'
+  - 'databricks/dolly-v1-6b'
+  - 'databricks/dolly-v2-7b'
+  - 'databricks/dolly-v2-12b'
+  - 'internlm/internlm-chat-7b'
+  - 'Qwen/Qwen-7B-Chat'
+  - 'BAAI/AquilaChat-7B'
+  - 'baichuan-inc/Baichuan2-7B-Chat'
+  - 'baichuan-inc/Baichuan2-13B-Chat-4bit'
+  - 'bigscience/bloomz-7b1'
 #  - 'fnlp/moss-moon-003-sft-4bit' # moss-moon-003-sft cannot work on transformers 4.34+
-  # - 'mistralai/Mistral-7B-v0.1'
+  - 'mistralai/Mistral-7B-v0.1'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3
@@ -34,5 +34,5 @@ cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu w
 exclude:
 #  - 'fnlp/moss-moon-003-sft-4bit:1024'
 #  - 'fnlp/moss-moon-003-sft-4bit:2048'
-  # - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
-  # - 'bigscience/bloomz-7b1:2048'
+  - 'baichuan-inc/Baichuan2-13B-Chat-4bit:2048'
+  - 'bigscience/bloomz-7b1:2048'
diff --git a/python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml b/python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml
@@ -1,9 +1,9 @@
 # For the models that require transformers 4.37.0
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
-  # - 'microsoft/phi-2'
-  # - 'microsoft/Phi-3-mini-4k-instruct'
-  # - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - 'microsoft/phi-2'
+  - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3

diff --git a/python/llm/test/benchmark/arc-perf-transformers-437.yaml b/python/llm/test/benchmark/arc-perf-transformers-437.yaml
@@ -1,9 +1,9 @@
 # For the models that require transformers 4.37.0
 repo_id:
   - 'Qwen/Qwen1.5-7B-Chat'
-  # - 'microsoft/phi-2'
-  # - 'microsoft/Phi-3-mini-4k-instruct'
-  # - 'meta-llama/Meta-Llama-3-8B-Instruct'
+  - 'microsoft/phi-2'
+  - 'microsoft/Phi-3-mini-4k-instruct'
+  - 'meta-llama/Meta-Llama-3-8B-Instruct'
 local_model_hub: '/mnt/disk1/models'
 warm_up: 1
 num_trials: 3