update default model to resolve the vllm/model_executor issue (#1985)

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

Author: chensuyue

DocSum/docker_compose/intel/cpu/xeon/compose.yaml

@@ -40,6 +40,7 @@ services:
       LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
       MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
       DocSum_COMPONENT_NAME: ${DocSum_COMPONENT_NAME}

DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml

@@ -40,6 +40,7 @@ services:
       LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
       MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
       DocSum_COMPONENT_NAME: ${DocSum_COMPONENT_NAME}

DocSum/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -45,6 +45,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
       MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
       LLM_ENDPOINT: ${LLM_ENDPOINT}

DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml

@@ -49,6 +49,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
       MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
       LLM_ENDPOINT: ${LLM_ENDPOINT}

DocSum/docker_compose/intel/set_env.sh

@@ -13,7 +13,7 @@ export https_proxy=$https_proxy
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 
 export LLM_ENDPOINT_PORT=8008
-export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export MAX_INPUT_TOKENS=1024
 export MAX_TOTAL_TOKENS=2048