feat: add qwen2.5 for model provider siliconflow (#8630)

This commit is contained in:
zhuhao 2024-09-22 16:42:34 +08:00 committed by GitHub
parent 2d869d6831
commit 45c0a44411
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 124 additions and 0 deletions

View File

@ -1,3 +1,7 @@
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2.5-14B-Instruct
- Qwen/Qwen2.5-32B-Instruct
- Qwen/Qwen2.5-72B-Instruct
- Qwen/Qwen2-72B-Instruct
- Qwen/Qwen2-57B-A14B-Instruct
- Qwen/Qwen2-7B-Instruct

View File

@ -0,0 +1,30 @@
model: Qwen/Qwen2.5-14B-Instruct
label:
en_US: Qwen/Qwen2.5-14B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
- name: max_tokens
use_template: max_tokens
type: int
default: 512
min: 1
max: 8192
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: '0.7'
output: '0.7'
unit: '0.000001'
currency: RMB

View File

@ -0,0 +1,30 @@
model: Qwen/Qwen2.5-32B-Instruct
label:
en_US: Qwen/Qwen2.5-32B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
- name: max_tokens
use_template: max_tokens
type: int
default: 512
min: 1
max: 8192
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: '1.26'
output: '1.26'
unit: '0.000001'
currency: RMB

View File

@ -0,0 +1,30 @@
model: Qwen/Qwen2.5-72B-Instruct
label:
en_US: Qwen/Qwen2.5-72B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
- name: max_tokens
use_template: max_tokens
type: int
default: 512
min: 1
max: 8192
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: '4.13'
output: '4.13'
unit: '0.000001'
currency: RMB

View File

@ -0,0 +1,30 @@
model: Qwen/Qwen2.5-7B-Instruct
label:
en_US: Qwen/Qwen2.5-7B-Instruct
model_type: llm
features:
- agent-thought
model_properties:
mode: chat
context_size: 32768
parameter_rules:
- name: temperature
use_template: temperature
- name: max_tokens
use_template: max_tokens
type: int
default: 512
min: 1
max: 8192
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'
output: '0'
unit: '0.000001'
currency: RMB