Add support for latest deepseek models on Gaudi (#1491)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
Liang Lv
2025-02-05 08:30:04 +08:00
committed by GitHub
parent a4d028e8ea
commit 9adf7a6af0
10 changed files with 14 additions and 5 deletions

View File

@@ -47,6 +47,7 @@ function start_services() {
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export NUM_CARDS=1
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"

View File

@@ -45,6 +45,7 @@ function start_services() {
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export NUM_CARDS=1
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export host_ip=${ip_address}

View File

@@ -46,6 +46,7 @@ function start_services() {
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export NUM_CARDS=1
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')

View File

@@ -45,6 +45,7 @@ function start_services() {
cd $WORKPATH/docker_compose/intel/hpu/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export NUM_CARDS=1
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}