Austin/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2024-11-16 03:32:23 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

chore: update Qwen model params (#2892)

Browse Source
This commit is contained in:
Su Yang 2024-03-19 18:13:32 +08:00 committed by GitHub
parent e9aa0e89d3
commit 8133ba16b1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 162 additions and 106 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-1201.yaml
View File

@ -8,55 +8,66 @@ model_properties:
parameter_rules:
- name: temperature
use_template: temperature
default: 1.0
type: float
default: 0.85
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: max_tokens
use_template: max_tokens
type: int
default: 2000
min: 1
max: 2000
help:
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
- name: top_p
use_template: top_p
type: float
default: 0.8
min: 0.1
max: 0.9
help:
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
- name: max_tokens
use_template: max_tokens
default: 1500
min: 1
max: 6000
help:
zh_Hans: 用于限制模型生成token的数量，max_tokens设置的是生成上限，并不表示一定会生成这么多的token数量。
en_US: It is used to limit the number of tokens generated by the model. max_tokens sets the upper limit of generation, which does not mean that so many tokens will be generated.
- name: top_k
type: int
min: 0
max: 99
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。默认不传递该参数，取值为None或当top_k大于100时，表示不启用top_k策略，此时，仅有top_p策略生效。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. This parameter is not passed by default. The value is None or when top_k is greater than 100, it means that the top_k policy is not enabled. At this time, only the top_p policy takes effect.
required: false
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
- name: seed
required: false
type: int
default: 1234
label:
zh_Hans: 随机种子
en_US: Random seed
type: int
help:
zh_Hans: 生成时，随机数的种子，用于控制模型生成的随机性。如果使用相同的种子，每次运行生成的结果都将相同；当需要复现模型的生成结果时，可以使用相同的种子。seed参数支持无符号64位整数类型。
en_US: When generating, the random number seed is used to control the randomness of model generation. If you use the same seed, the results generated by each run will be the same; when you need to reproduce the results of the model, you can use the same seed. The seed parameter supports unsigned 64-bit integer types.
required: false
zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
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: repetition_penalty
label:
en_US: Repetition penalty
required: false
type: float
default: 1.1
label:
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 repetition of model generation. Increasing the repetition_penalty can reduce the repetition of model generation. 1.0 means no punishment.
required: false
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
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:

55
api/core/model_runtime/model_providers/tongyi/llm/qwen-max-longcontext.yaml
View File

@ -4,59 +4,70 @@ label:
model_type: llm
model_properties:
mode: chat
context_size: 30000
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
default: 1.0
type: float
default: 0.85
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: max_tokens
use_template: max_tokens
type: int
default: 2000
min: 1
max: 2000
help:
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
- name: top_p
use_template: top_p
type: float
default: 0.8
min: 0.1
max: 0.9
help:
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
- name: max_tokens
use_template: max_tokens
default: 2000
min: 1
max: 28000
help:
zh_Hans: 用于限制模型生成token的数量，max_tokens设置的是生成上限，并不表示一定会生成这么多的token数量。
en_US: It is used to limit the number of tokens generated by the model. max_tokens sets the upper limit of generation, which does not mean that so many tokens will be generated.
- name: top_k
type: int
min: 0
max: 99
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。默认不传递该参数，取值为None或当top_k大于100时，表示不启用top_k策略，此时，仅有top_p策略生效。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. This parameter is not passed by default. The value is None or when top_k is greater than 100, it means that the top_k policy is not enabled. At this time, only the top_p policy takes effect.
required: false
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
- name: seed
required: false
type: int
default: 1234
label:
zh_Hans: 随机种子
en_US: Random seed
type: int
help:
zh_Hans: 生成时，随机数的种子，用于控制模型生成的随机性。如果使用相同的种子，每次运行生成的结果都将相同；当需要复现模型的生成结果时，可以使用相同的种子。seed参数支持无符号64位整数类型。
en_US: When generating, the random number seed is used to control the randomness of model generation. If you use the same seed, the results generated by each run will be the same; when you need to reproduce the results of the model, you can use the same seed. The seed parameter supports unsigned 64-bit integer types.
required: false
zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
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: repetition_penalty
label:
en_US: Repetition penalty
required: false
type: float
default: 1.1
label:
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 repetition of model generation. Increasing the repetition_penalty can reduce the repetition of model generation. 1.0 means no punishment.
required: false
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
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:

53
api/core/model_runtime/model_providers/tongyi/llm/qwen-max.yaml
View File

@ -8,55 +8,66 @@ model_properties:
parameter_rules:
- name: temperature
use_template: temperature
default: 1.0
type: float
default: 0.85
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: max_tokens
use_template: max_tokens
type: int
default: 2000
min: 1
max: 2000
help:
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
- name: top_p
use_template: top_p
type: float
default: 0.8
min: 0.1
max: 0.9
help:
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
- name: max_tokens
use_template: max_tokens
default: 1500
min: 1
max: 6000
help:
zh_Hans: 用于限制模型生成token的数量，max_tokens设置的是生成上限，并不表示一定会生成这么多的token数量。
en_US: It is used to limit the number of tokens generated by the model. max_tokens sets the upper limit of generation, which does not mean that so many tokens will be generated.
- name: top_k
type: int
min: 0
max: 99
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。默认不传递该参数，取值为None或当top_k大于100时，表示不启用top_k策略，此时，仅有top_p策略生效。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. This parameter is not passed by default. The value is None or when top_k is greater than 100, it means that the top_k policy is not enabled. At this time, only the top_p policy takes effect.
required: false
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
- name: seed
required: false
type: int
default: 1234
label:
zh_Hans: 随机种子
en_US: Random seed
type: int
help:
zh_Hans: 生成时，随机数的种子，用于控制模型生成的随机性。如果使用相同的种子，每次运行生成的结果都将相同；当需要复现模型的生成结果时，可以使用相同的种子。seed参数支持无符号64位整数类型。
en_US: When generating, the random number seed is used to control the randomness of model generation. If you use the same seed, the results generated by each run will be the same; when you need to reproduce the results of the model, you can use the same seed. The seed parameter supports unsigned 64-bit integer types.
required: false
zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
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: repetition_penalty
label:
en_US: Repetition penalty
required: false
type: float
default: 1.1
label:
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 repetition of model generation. Increasing the repetition_penalty can reduce the repetition of model generation. 1.0 means no punishment.
required: false
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
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:

54
api/core/model_runtime/model_providers/tongyi/llm/qwen-plus.yaml
View File

@ -4,58 +4,70 @@ label:
model_type: llm
model_properties:
mode: completion
context_size: 32000
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
default: 1.0
type: float
default: 0.85
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: max_tokens
use_template: max_tokens
type: int
default: 1500
min: 1
max: 1500
help:
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
- name: top_p
use_template: top_p
type: float
default: 0.8
min: 0.1
max: 0.9
help:
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
- name: max_tokens
use_template: max_tokens
default: 2000
min: 1
max: 30000
help:
zh_Hans: 用于限制模型生成token的数量，max_tokens设置的是生成上限，并不表示一定会生成这么多的token数量。
en_US: It is used to limit the number of tokens generated by the model. max_tokens sets the upper limit of generation, which does not mean that so many tokens will be generated.
- name: top_k
type: int
min: 0
max: 99
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。默认不传递该参数，取值为None或当top_k大于100时，表示不启用top_k策略，此时，仅有top_p策略生效。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. This parameter is not passed by default. The value is None or when top_k is greater than 100, it means that the top_k policy is not enabled. At this time, only the top_p policy takes effect.
required: false
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
- name: seed
required: false
type: int
default: 1234
label:
zh_Hans: 随机种子
en_US: Random seed
type: int
help:
zh_Hans: 生成时，随机数的种子，用于控制模型生成的随机性。如果使用相同的种子，每次运行生成的结果都将相同；当需要复现模型的生成结果时，可以使用相同的种子。seed参数支持无符号64位整数类型。
en_US: When generating, the random number seed is used to control the randomness of model generation. If you use the same seed, the results generated by each run will be the same; when you need to reproduce the results of the model, you can use the same seed. The seed parameter supports unsigned 64-bit integer types.
required: false
zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
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: repetition_penalty
label:
en_US: Repetition penalty
required: false
type: float
default: 1.1
label:
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 repetition of model generation. Increasing the repetition_penalty can reduce the repetition of model generation. 1.0 means no punishment.
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
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:

53
api/core/model_runtime/model_providers/tongyi/llm/qwen-turbo.yaml
View File

@ -8,55 +8,66 @@ model_properties:
parameter_rules:
- name: temperature
use_template: temperature
default: 1.0
type: float
default: 0.85
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: max_tokens
use_template: max_tokens
type: int
default: 1500
min: 1
max: 1500
help:
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
- name: top_p
use_template: top_p
type: float
default: 0.8
min: 0.1
max: 0.9
help:
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
- name: max_tokens
use_template: max_tokens
default: 1500
min: 1
max: 6000
help:
zh_Hans: 用于限制模型生成token的数量，max_tokens设置的是生成上限，并不表示一定会生成这么多的token数量。
en_US: It is used to limit the number of tokens generated by the model. max_tokens sets the upper limit of generation, which does not mean that so many tokens will be generated.
- name: top_k
type: int
min: 0
max: 99
label:
zh_Hans: 取样数量
en_US: Top k
type: int
help:
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。默认不传递该参数，取值为None或当top_k大于100时，表示不启用top_k策略，此时，仅有top_p策略生效。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated. This parameter is not passed by default. The value is None or when top_k is greater than 100, it means that the top_k policy is not enabled. At this time, only the top_p policy takes effect.
required: false
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
- name: seed
required: false
type: int
default: 1234
label:
zh_Hans: 随机种子
en_US: Random seed
type: int
help:
zh_Hans: 生成时，随机数的种子，用于控制模型生成的随机性。如果使用相同的种子，每次运行生成的结果都将相同；当需要复现模型的生成结果时，可以使用相同的种子。seed参数支持无符号64位整数类型。
en_US: When generating, the random number seed is used to control the randomness of model generation. If you use the same seed, the results generated by each run will be the same; when you need to reproduce the results of the model, you can use the same seed. The seed parameter supports unsigned 64-bit integer types.
required: false
zh_Hans: 生成时使用的随机数种子，用户控制模型生成内容的随机性。支持无符号64位整数，默认值为 1234。在使用seed时，模型将尽可能生成相同或相似的结果，但目前不保证每次生成的结果完全相同。
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: repetition_penalty
label:
en_US: Repetition penalty
required: false
type: float
default: 1.1
label:
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 repetition of model generation. Increasing the repetition_penalty can reduce the repetition of model generation. 1.0 means no punishment.
required: false
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
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: