Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| a27225c1ea |
@@ -1,4 +1,3 @@
|
||||
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
@@ -31,7 +30,7 @@ services:
|
||||
ports:
|
||||
- "3006:80"
|
||||
volumes:
|
||||
- "${MODEL_CACHE:-./data}:/data"
|
||||
- "./data:/data"
|
||||
shm_size: 1g
|
||||
environment:
|
||||
no_proxy: ${no_proxy}
|
||||
|
||||
@@ -40,7 +40,6 @@ 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}
|
||||
|
||||
@@ -40,7 +40,6 @@ 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}
|
||||
|
||||
@@ -45,7 +45,6 @@ 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}
|
||||
|
||||
@@ -49,7 +49,6 @@ 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: ${LLM_ENDPOINT}
|
||||
|
||||
@@ -13,7 +13,7 @@ export https_proxy=$https_proxy
|
||||
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
|
||||
|
||||
export LLM_ENDPOINT_PORT=8008
|
||||
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
|
||||
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
|
||||
export MAX_INPUT_TOKENS=1024
|
||||
export MAX_TOTAL_TOKENS=2048
|
||||
|
||||
|
||||
Reference in New Issue
Block a user