| .. |
|
__base
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
anthropic
|
6333cf43a8
fix: anthropic messages empty raise errors (#1893)
|
1 year ago |
|
azure_openai
|
18af84e193
fix: array oob in azure openai embeddings (#1905)
|
1 year ago |
|
baichuan
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
chatglm
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
cohere
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
google
|
ede69b4659
fix: gemini block error (#1877)
|
1 year ago |
|
huggingface_hub
|
91ee62d1ab
fix: huggingface and replicate. (#1888)
|
1 year ago |
|
jina
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
localai
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
minimax
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
openai
|
4d502ea44d
fix: openai embedding list out of bound (#1879)
|
1 year ago |
|
openai_api_compatible
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
openllm
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
replicate
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
spark
|
7c7ee633c1
fix: spark credentials validate (#1906)
|
1 year ago |
|
tongyi
|
025b859c7e
fix: tongyi generate error (#1904)
|
1 year ago |
|
wenxin
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
xinference
|
5a756ca981
fix: xinference cache (#1926)
|
1 year ago |
|
zhipuai
|
0c5892bcb6
fix: zhipuai chatglm turbo prompts must user, assistant in sequence (#1899)
|
1 year ago |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
_position.yaml
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
model_provider_factory.py
|
3fa5204b0c
feat: optimize performance (#1928)
|
1 year ago |
takatost
3fa5204b0c
feat: optimize performance (#1928)