From c7a918bbc951c06db8106ccb78ff81da68a1a290 Mon Sep 17 00:00:00 2001 From: chensuyue Date: Wed, 21 May 2025 17:35:26 +0800 Subject: [PATCH] update default model name to resolve the vllm/model_executor issue Signed-off-by: chensuyue --- DocSum/docker_compose/intel/cpu/xeon/compose.yaml | 1 + DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml | 1 + DocSum/docker_compose/intel/hpu/gaudi/compose.yaml | 1 + DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml | 1 + DocSum/docker_compose/intel/set_env.sh | 2 +- 5 files changed, 5 insertions(+), 1 deletion(-) diff --git a/DocSum/docker_compose/intel/cpu/xeon/compose.yaml b/DocSum/docker_compose/intel/cpu/xeon/compose.yaml index 8eb3bb28b6..9f05963e7a 100644 --- a/DocSum/docker_compose/intel/cpu/xeon/compose.yaml +++ b/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} diff --git a/DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml b/DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml index 4b0362bd09..2343d726c7 100644 --- a/DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml +++ b/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} diff --git a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml b/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml index f44d789a93..2efa09e890 100644 --- a/DocSum/docker_compose/intel/hpu/gaudi/compose.yaml +++ b/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} diff --git a/DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml b/DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml index 01008de27a..6b922ebc68 100644 --- a/DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml +++ b/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: ${LLM_ENDPOINT} diff --git a/DocSum/docker_compose/intel/set_env.sh b/DocSum/docker_compose/intel/set_env.sh index b31ceb5784..d2c061177d 100644 --- a/DocSum/docker_compose/intel/set_env.sh +++ b/DocSum/docker_compose/intel/set_env.sh @@ -13,7 +13,7 @@ export https_proxy=$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