AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-05-10 04:19:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

add Qwen model translate (#8674)

Browse Source
This commit is contained in:
AAEE86 2024-09-23 16:18:55 +08:00 committed by GitHub
parent b37954b966
commit c66cecaa55
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
49 changed files with 326 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/model_runtime/model_providers/tongyi/llm/farui-plus.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo-0919.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo-latest.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-coder-turbo.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-long.yaml
View File

@ -63,6 +63,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -70,6 +71,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus-0816.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus-0919.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus-latest.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-plus.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-turbo-0919.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-turbo-latest.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-math-turbo.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0107.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0403.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0428.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-0919.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-latest.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0206.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0624.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0723.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0806.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-0919.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-chat.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus-latest.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0206.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0624.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-0919.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-chat.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo-latest.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
View File

@ -62,6 +62,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -69,6 +70,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

30
api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-max-0809.yaml
View File

@ -9,6 +9,15 @@ model_properties:
mode: chat
context_size: 32000
parameter_rules:
- name: temperature
use_template: temperature
type: float
default: 0.3
min: 0.0
max: 2.0
help:
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
- name: top_p
use_template: top_p
type: float
@ -50,6 +59,27 @@ parameter_rules:
en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
- name: response_format
use_template: response_format
- name: repetition_penalty
required: false
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
- name: response_format
use_template: response_format
pricing:
input: '0.02'
output: '0.02'

30
api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-max.yaml
View File

@ -9,6 +9,15 @@ model_properties:
mode: chat
context_size: 32000
parameter_rules:
- name: temperature
use_template: temperature
type: float
default: 0.3
min: 0.0
max: 2.0
help:
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
- name: top_p
use_template: top_p
type: float
@ -50,6 +59,27 @@ parameter_rules:
en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
- name: response_format
use_template: response_format
- name: repetition_penalty
required: false
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
- name: response_format
use_template: response_format
pricing:
input: '0.02'
output: '0.02'

30
api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-plus-0201.yaml
View File

@ -9,6 +9,15 @@ model_properties:
mode: chat
context_size: 8000
parameter_rules:
- name: temperature
use_template: temperature
type: float
default: 0.3
min: 0.0
max: 2.0
help:
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
- name: top_p
use_template: top_p
type: float
@ -50,6 +59,27 @@ parameter_rules:
en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
- name: response_format
use_template: response_format
- name: repetition_penalty
required: false
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
- name: response_format
use_template: response_format
pricing:
input: '0.02'
output: '0.02'

30
api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-plus-0809.yaml
View File

@ -9,6 +9,15 @@ model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
type: float
default: 0.3
min: 0.0
max: 2.0
help:
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
- name: top_p
use_template: top_p
type: float
@ -50,6 +59,27 @@ parameter_rules:
en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
- name: response_format
use_template: response_format
- name: repetition_penalty
required: false
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
- name: response_format
use_template: response_format
pricing:
input: '0.008'
output: '0.008'

30
api/core/model_runtime/model_providers/tongyi/llm/qwen-vl-plus.yaml
View File

@ -9,6 +9,15 @@ model_properties:
mode: chat
context_size: 8000
parameter_rules:
- name: temperature
use_template: temperature
type: float
default: 0.3
min: 0.0
max: 2.0
help:
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
- name: top_p
use_template: top_p
type: float
@ -50,6 +59,27 @@ parameter_rules:
en_US: The random number seed used when generating, the user controls the randomness of the content generated by the model. Supports unsigned 64-bit integers, default value is 1234. When using seed, the model will try its best to generate the same or similar results, but there is currently no guarantee that the results will be exactly the same every time.
- name: response_format
use_template: response_format
- name: repetition_penalty
required: false
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
- name: response_format
use_template: response_format
pricing:
input: '0.008'
output: '0.008'

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2-math-1.5b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2-math-72b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2-math-7b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-0.5b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-1.5b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-14b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-32b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-3b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-72b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-7b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.

4
api/core/model_runtime/model_providers/tongyi/llm/qwen2.5-coder-7b-instruct.yaml
View File

@ -60,6 +60,7 @@ parameter_rules:
type: float
default: 1.1
label:
zh_Hans: 重复惩罚
en_US: Repetition penalty
help:
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
@ -67,6 +68,9 @@ parameter_rules:
- name: enable_search
type: boolean
default: false
label:
zh_Hans: 联网搜索
en_US: Web Search
help:
zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.