Compare commits

..

1 Commits

Author SHA1 Message Date
a27225c1ea Update AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml
Some checks failed
Create an issue to GenAIInfra on push / Create issue (push) Has been cancelled
Nightly build/publish latest docker images / get-build-matrix (push) Has been cancelled
Nightly build/publish latest docker images / build-comps-base (push) Has been cancelled
Nightly build/publish latest docker images / build-images (push) Has been cancelled
Nightly build/publish latest docker images / test-example (push) Has been cancelled
Nightly build/publish latest docker images / get-image-list (push) Has been cancelled
Nightly build/publish latest docker images / publish (push) Has been cancelled
Trellix Command Line Scanner / Trellix (push) Has been cancelled
Weekly test all examples on multiple HWs / get-test-matrix (push) Has been cancelled
Weekly test all examples on multiple HWs / build-comps-base (push) Has been cancelled
Weekly test all examples on multiple HWs / run-examples (push) Has been cancelled
Update Docker Hub Description / get-images-matrix (push) Has been cancelled
Update Docker Hub Description / check-images-matrix (push) Has been cancelled
Update Docker Hub Description / dockerHubDescription (push) Has been cancelled
Check stale issue and pr / close-issues (push) Has been cancelled
Daily update vLLM & vLLM-fork version / freeze-tag (vLLM, vllm-project/vllm, VLLM_VER) (push) Has been cancelled
Daily update vLLM & vLLM-fork version / freeze-tag (vLLM-fork, HabanaAI/vllm-fork, VLLM_FORK_VER) (push) Has been cancelled
2025-05-21 18:48:26 +00:00
6 changed files with 2 additions and 7 deletions

View File

@@ -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}

View File

@@ -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}

View File

@@ -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}

View File

@@ -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}

View File

@@ -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}

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="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