update

Signed-off-by: minmingzhu <[email protected]>

Author: minmingzhu

.github/workflows/workflow_finetune.yml

@@ -146,7 +146,7 @@ jobs:
 
       - name: Run Deltatuner Test on DENAS-LoRA Model
         run: |
-          if [[ ${{ matrix.model }} =~ ^(mosaicml\/mpt-7b-chat|huggyllama\/llama-7b|meta-llama\/Llama-2-7b-chat-hf|mistralai\/Mistral-7B-v0.1|google\/gemma-2b)$ ]]; then
+          if [[ ${{ matrix.model }} =~ ^(mosaicml\/mpt-7b-chat|huggyllama\/llama-7b|meta-llama\/Llama-2-7b-chat-hf|mistralai\/Mistral-7B-v0.1|mistralai\/Mixtral-8x7B-Instruct-v0.1)$ ]]; then
             echo ${{ matrix.model }} is not supported!
           else
             docker exec "finetune" bash -c "rm -rf /tmp/llm-ray/*"

.github/workflows/workflow_inference.yml

@@ -159,7 +159,7 @@ jobs:
       - name: Run Inference Test with DeepSpeed
         run: |
           TARGET=${{steps.target.outputs.target}}
-          if [[ ${{ matrix.model }} =~ ^(gpt2|falcon-7b|starcoder|mpt-7b.*)$ ]]; then
+          if [[ ${{ matrix.model }} =~ ^(mixtral-8x7b-Instruct-v0.1|gpt2|falcon-7b|starcoder|mpt-7b.*)$ ]]; then
             echo ${{ matrix.model }} is not supported!
           elif [[ ! ${{ matrix.model }} == "llama-2-7b-chat-hf-vllm" ]]; then
             docker exec "${TARGET}" bash -c "python .github/workflows/config/update_inference_config.py --config_file llm_on_ray/inference/models/\"${{ matrix.model }}\".yaml --output_file \"${{ matrix.model }}\".yaml.deepspeed --deepspeed"
@@ -172,7 +172,7 @@ jobs:
         if: ${{ matrix.dtuner_model }}
         run: |
           TARGET=${{steps.target.outputs.target}}
-          if [[ ${{ matrix.model }} =~ ^(gpt2|falcon-7b|starcoder|mpt-7b.*)$ ]]; then
+          if [[ ${{ matrix.model }} =~ ^(mixtral-8x7b-Instruct-v0.1|gpt2|falcon-7b|starcoder|mpt-7b.*)$ ]]; then
             echo ${{ matrix.model }} is not supported!
           else
             docker exec "${TARGET}" bash -c "llm_on_ray-serve --config_file .github/workflows/config/mpt_deltatuner_deepspeed.yaml --simple"

pyproject.toml

@@ -39,7 +39,7 @@ dependencies = [
 
 [project.optional-dependencies]
 cpu = [
-    "transformers>=4.35.0, <=4.35.2",
+    "transformers>=4.36.0, <=4.38.1",
     "intel_extension_for_pytorch>=2.2.0",
     "torch>=2.2.0",
     "oneccl_bind_pt>=2.2.0"