更新model_settings:重新启用xinterface

This commit is contained in:
GuanYuankai 2025-03-04 09:19:37 +08:00
parent 0bff316575
commit ac368b3814
1 changed files with 67 additions and 67 deletions

View File

@ -2,7 +2,7 @@
# 默认选用的 LLM 名称
DEFAULT_LLM_MODEL: qwen2-instruct
DEFAULT_LLM_MODEL: qwen2.5-instruct
# 默认选用的 Embedding 名称
DEFAULT_EMBEDDING_MODEL: bge-large-zh-v1.5
@ -112,78 +112,78 @@ LLM_MODEL_CONFIG:
MODEL_PLATFORMS:
- platform_name: xinference
platform_type: xinference
api_base_url: http://127.0.0.1:9997/v1
api_base_url: http://192.168.0.21:9997/v1
api_key: EMPTY
api_proxy: ''
api_concurrencies: 5
auto_detect_model: true
llm_models: []
embed_models: []
text2image_models: []
image2text_models: []
rerank_models: [bge-reranker-large]
speech2text_models: []
text2speech_models: []
- platform_name: ollama
platform_type: ollama
api_base_url: http://127.0.0.1:11434/v1
api_key: EMPTY
api_proxy: ''
api_concurrencies: 5
auto_detect_model: false
llm_models:
- qwen:7b
- qwen2:7b
embed_models:
- quentinz/bge-large-zh-v1.5
text2image_models: []
image2text_models: []
rerank_models: []
speech2text_models: []
text2speech_models: []
- platform_name: oneapi
platform_type: oneapi
api_base_url: http://127.0.0.1:3000/v1
api_key: sk-
api_proxy: ''
api_concurrencies: 5
auto_detect_model: false
llm_models:
- chatglm_pro
- chatglm_turbo
- chatglm_std
- chatglm_lite
- qwen-turbo
- qwen-plus
- qwen-max
- qwen-max-longcontext
- ERNIE-Bot
- ERNIE-Bot-turbo
- ERNIE-Bot-4
- SparkDesk
embed_models:
- text-embedding-v1
- Embedding-V1
text2image_models: []
image2text_models: []
rerank_models: []
speech2text_models: []
text2speech_models: []
- platform_name: openai
platform_type: openai
api_base_url: https://api.openai.com/v1
api_key: sk-proj-
api_proxy: ''
api_concurrencies: 5
auto_detect_model: false
llm_models:
- gpt-4o
- gpt-3.5-turbo
embed_models:
- text-embedding-3-small
- text-embedding-3-large
llm_models: [qwen2.5-instruct]
embed_models: [bge-large-zh-v1.5]
text2image_models: []
image2text_models: []
rerank_models: []
speech2text_models: []
text2speech_models: []
# - platform_name: ollama
# platform_type: ollama
# api_base_url: http://127.0.0.1:11434/v1
# api_key: EMPTY
# api_proxy: ''
# api_concurrencies: 5
# auto_detect_model: false
# llm_models:
# - qwen:7b
# - qwen2:7b
# embed_models:
# - quentinz/bge-large-zh-v1.5
# text2image_models: []
# image2text_models: []
# rerank_models: []
# speech2text_models: []
# text2speech_models: []
# - platform_name: oneapi
# platform_type: oneapi
# api_base_url: http://127.0.0.1:3000/v1
# api_key: sk-
# api_proxy: ''
# api_concurrencies: 5
# auto_detect_model: false
# llm_models:
# - chatglm_pro
# - chatglm_turbo
# - chatglm_std
# - chatglm_lite
# - qwen-turbo
# - qwen-plus
# - qwen-max
# - qwen-max-longcontext
# - ERNIE-Bot
# - ERNIE-Bot-turbo
# - ERNIE-Bot-4
# - SparkDesk
# embed_models:
# - text-embedding-v1
# - Embedding-V1
# text2image_models: []
# image2text_models: []
# rerank_models: []
# speech2text_models: []
# text2speech_models: []
# - platform_name: openai
# platform_type: openai
# api_base_url: https://api.openai.com/v1
# api_key: sk-proj-
# api_proxy: ''
# api_concurrencies: 5
# auto_detect_model: false
# llm_models:
# - gpt-4o
# - gpt-3.5-turbo
# embed_models:
# - text-embedding-3-small
# - text-embedding-3-large
# text2image_models: []
# image2text_models: []
# rerank_models: []
# speech2text_models: []
# text2speech_models: []