feat: support predefined models for openrouter (#5494)
sino
2 years ago
committed by
GitHub
parent
f7900f298f
commit
877a2c144b
@ -0,0 +1,21 @@
|
||||
- openai/gpt-4o
|
||||
- openai/gpt-4
|
||||
- openai/gpt-4-32k
|
||||
- openai/gpt-3.5-turbo
|
||||
- anthropic/claude-3.5-sonnet
|
||||
- anthropic/claude-3-haiku
|
||||
- anthropic/claude-3-opus
|
||||
- anthropic/claude-3-sonnet
|
||||
- google/gemini-pro-1.5
|
||||
- google/gemini-flash-1.5
|
||||
- google/gemini-pro
|
||||
- cohere/command-r-plus
|
||||
- cohere/command-r
|
||||
- meta-llama/llama-3-70b-instruct
|
||||
- meta-llama/llama-3-8b-instruct
|
||||
- mistralai/mixtral-8x22b-instruct
|
||||
- mistralai/mixtral-8x7b-instruct
|
||||
- mistralai/mistral-7b-instruct
|
||||
- qwen/qwen-2-72b-instruct
|
||||
- deepseek/deepseek-chat
|
||||
- deepseek/deepseek-coder
|
||||
@ -0,0 +1,39 @@
|
||||
model: anthropic/claude-3.5-sonnet
|
||||
label:
|
||||
en_US: claude-3.5-sonnet
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "3.00"
|
||||
output: "15.00"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,39 @@
|
||||
model: anthropic/claude-3-haiku
|
||||
label:
|
||||
en_US: claude-3-haiku
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "0.25"
|
||||
output: "1.25"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,39 @@
|
||||
model: anthropic/claude-3-opus
|
||||
label:
|
||||
en_US: claude-3-opus
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "15.00"
|
||||
output: "75.00"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,39 @@
|
||||
model: anthropic/claude-3-sonnet
|
||||
label:
|
||||
en_US: claude-3-sonnet
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "3.00"
|
||||
output: "15.00"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,45 @@
|
||||
model: cohere/command-r-plus
|
||||
label:
|
||||
en_US: command-r-plus
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
max: 5.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 0.75
|
||||
min: 0.01
|
||||
max: 0.99
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
default: 0
|
||||
min: 0
|
||||
max: 500
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
max: 4096
|
||||
pricing:
|
||||
input: "3"
|
||||
output: "15"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,45 @@
|
||||
model: cohere/command-r
|
||||
label:
|
||||
en_US: command-r
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
max: 5.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 0.75
|
||||
min: 0.01
|
||||
max: 0.99
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
default: 0
|
||||
min: 0
|
||||
max: 500
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
max: 4096
|
||||
pricing:
|
||||
input: "0.5"
|
||||
output: "1.5"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,30 @@
|
||||
model: deepseek/deepseek-coder
|
||||
label:
|
||||
en_US: deepseek-coder
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 4096
|
||||
default: 1024
|
||||
pricing:
|
||||
input: "0.14"
|
||||
output: "0.28"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,39 @@
|
||||
model: google/gemini-flash-1.5
|
||||
label:
|
||||
en_US: gemini-flash-1.5
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "0.25"
|
||||
output: "0.75"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,39 @@
|
||||
model: google/gemini-pro-1.5
|
||||
label:
|
||||
en_US: gemini-pro-1.5
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "2.5"
|
||||
output: "7.5"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,38 @@
|
||||
model: google/gemini-pro
|
||||
label:
|
||||
en_US: gemini-pro
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 30720
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 2048
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "0.125"
|
||||
output: "0.375"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,42 @@
|
||||
model: openai/gpt-3.5-turbo
|
||||
label:
|
||||
en_US: gpt-3.5-turbo
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 16385
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "0.5"
|
||||
output: "1.5"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,57 @@
|
||||
model: openai/gpt-4-32k
|
||||
label:
|
||||
en_US: gpt-4-32k
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 32768
|
||||
- name: seed
|
||||
label:
|
||||
zh_Hans: 种子
|
||||
en_US: Seed
|
||||
type: int
|
||||
help:
|
||||
zh_Hans:
|
||||
如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint
|
||||
响应参数来监视变化。
|
||||
en_US:
|
||||
If specified, model will make a best effort to sample deterministically,
|
||||
such that repeated requests with the same seed and parameters should return
|
||||
the same result. Determinism is not guaranteed, and you should refer to the
|
||||
system_fingerprint response parameter to monitor changes in the backend.
|
||||
required: false
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "60"
|
||||
output: "120"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,57 @@
|
||||
model: openai/gpt-4
|
||||
label:
|
||||
en_US: gpt-4
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: seed
|
||||
label:
|
||||
zh_Hans: 种子
|
||||
en_US: Seed
|
||||
type: int
|
||||
help:
|
||||
zh_Hans:
|
||||
如果指定，模型将尽最大努力进行确定性采样，使得重复的具有相同种子和参数的请求应该返回相同的结果。不能保证确定性，您应该参考 system_fingerprint
|
||||
响应参数来监视变化。
|
||||
en_US:
|
||||
If specified, model will make a best effort to sample deterministically,
|
||||
such that repeated requests with the same seed and parameters should return
|
||||
the same result. Determinism is not guaranteed, and you should refer to the
|
||||
system_fingerprint response parameter to monitor changes in the backend.
|
||||
required: false
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "30"
|
||||
output: "60"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,43 @@
|
||||
model: openai/gpt-4o
|
||||
label:
|
||||
en_US: gpt-4o
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 4096
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "5.00"
|
||||
output: "15.00"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,23 @@
|
||||
model: meta-llama/llama-3-70b-instruct
|
||||
label:
|
||||
en_US: llama-3-70b-instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: "0.59"
|
||||
output: "0.79"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,23 @@
|
||||
model: meta-llama/llama-3-8b-instruct
|
||||
label:
|
||||
en_US: llama-3-8b-instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: "0.07"
|
||||
output: "0.07"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,30 @@
|
||||
model: mistralai/mistral-7b-instruct
|
||||
label:
|
||||
en_US: mistral-7b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 8000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.7
|
||||
min: 0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 1
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: "0.07"
|
||||
output: "0.07"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,30 @@
|
||||
model: mistralai/mixtral-8x22b-instruct
|
||||
label:
|
||||
en_US: mixtral-8x22b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 64000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.7
|
||||
min: 0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 1
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 8000
|
||||
pricing:
|
||||
input: "0.65"
|
||||
output: "0.65"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,31 @@
|
||||
model: mistralai/mixtral-8x7b-instruct
|
||||
label:
|
||||
zh_Hans: mixtral-8x7b-instruct
|
||||
en_US: mixtral-8x7b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.7
|
||||
min: 0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 1
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 8000
|
||||
pricing:
|
||||
input: "0.24"
|
||||
output: "0.24"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@ -0,0 +1,30 @@
|
||||
model: qwen/qwen-2-72b-instruct
|
||||
label:
|
||||
en_US: qwen-2-72b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 512
|
||||
min: 1
|
||||
max: 4096
|
||||
help:
|
||||
zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
|
||||
en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
pricing:
|
||||
input: "0.59"
|
||||
output: "0.79"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
Loading…
Reference in New Issue