jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

update default model name to resolve the vllm/model_executor issue

Browse Source 
Signed-off-by: chensuyue <suyue.chen@intel.com>
This commit is contained in:
chensuyue
2025-05-21 17:35:26 +08:00
parent c70b021689
commit c7a918bbc9
5 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
DocSum/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -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}

1
DocSum/docker_compose/intel/cpu/xeon/compose_tgi.yaml
View File

@@ -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}

1
DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -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}

1
DocSum/docker_compose/intel/hpu/gaudi/compose_tgi.yaml
View File

@@ -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}

2
DocSum/docker_compose/intel/set_env.sh
View File

@@ -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