Skip to content

Commit 56434db

Browse files
xander-artxanderdong
xander-art
and
xanderdong
authored
feat:add hunyuan model(hunyuan-role, hunyuan-large, hunyuan-large-rol… (#11766)
Co-authored-by: xanderdong <[email protected]>
1 parent 688292e commit 56434db

9 files changed

+276
-2
lines changed

‎api/core/model_runtime/model_providers/hunyuan/hunyuan.yaml

+2-2
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,8 @@ label:
33
zh_Hans: 腾讯混元
44
en_US: Hunyuan
55
description:
6-
en_US: Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro and hunyuan-lite.
7-
zh_Hans: 腾讯混元提供的模型，例如 hunyuan-standard、 hunyuan-standard-256k, hunyuan-pro 和 hunyuan-lite。
6+
en_US: Models provided by Tencent Hunyuan, such as hunyuan-standard, hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall and hunyuan-lite.
7+
zh_Hans: 腾讯混元提供的模型，例如 hunyuan-standard、 hunyuan-standard-256k, hunyuan-pro, hunyuan-role, hunyuan-large, hunyuan-large-role, hunyuan-turbo-latest, hunyuan-large-longcontext, hunyuan-turbo, hunyuan-vision, hunyuan-turbo-vision, hunyuan-functioncall 和 hunyuan-lite。
88
icon_small:
99
en_US: icon_s_en.png
1010
icon_large:

‎api/core/model_runtime/model_providers/hunyuan/llm/_position.yaml

+7
Original file line numberDiff line numberDiff line change
@@ -4,3 +4,10 @@
44
- hunyuan-pro
55
- hunyuan-turbo
66
- hunyuan-vision
7+
- hunyuan-role
8+
- hunyuan-large
9+
- hunyuan-large-role
10+
- hunyuan-large-longcontext
11+
- hunyuan-turbo-latest
12+
- hunyuan-turbo-vision
13+
- hunyuan-functioncall

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-functioncall.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-functioncall
2+
label:
3+
zh_Hans: hunyuan-functioncall
4+
en_US: hunyuan-functioncall
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 32000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 32000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.004'
36+
output: '0.008'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-large-longcontext.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-large-longcontext
2+
label:
3+
zh_Hans: hunyuan-large-longcontext
4+
en_US: hunyuan-large-longcontext
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 134000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 134000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.006'
36+
output: '0.018'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-large-role.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-large-role
2+
label:
3+
zh_Hans: hunyuan-large-role
4+
en_US: hunyuan-large-role
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 32000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 32000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.004'
36+
output: '0.008'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-large.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-large
2+
label:
3+
zh_Hans: hunyuan-large
4+
en_US: hunyuan-large
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 32000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 32000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.004'
36+
output: '0.012'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-role.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-role
2+
label:
3+
zh_Hans: hunyuan-role
4+
en_US: hunyuan-role
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 32000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 32000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.004'
36+
output: '0.008'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-turbo-latest.yaml

+38
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,38 @@
1+
model: hunyuan-turbo-latest
2+
label:
3+
zh_Hans: hunyuan-turbo-latest
4+
en_US: hunyuan-turbo-latest
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
model_properties:
12+
mode: chat
13+
context_size: 32000
14+
parameter_rules:
15+
- name: temperature
16+
use_template: temperature
17+
- name: top_p
18+
use_template: top_p
19+
- name: max_tokens
20+
use_template: max_tokens
21+
default: 1024
22+
min: 1
23+
max: 32000
24+
- name: enable_enhance
25+
label:
26+
zh_Hans: 功能增强
27+
en_US: Enable Enhancement
28+
type: boolean
29+
help:
30+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
31+
en_US: Allow the model to perform external search to enhance the generation results.
32+
required: false
33+
default: true
34+
pricing:
35+
input: '0.015'
36+
output: '0.05'
37+
unit: '0.001'
38+
currency: RMB

‎api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-turbo-vision.yaml

+39
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
model: hunyuan-turbo-vision
2+
label:
3+
zh_Hans: hunyuan-turbo-vision
4+
en_US: hunyuan-turbo-vision
5+
model_type: llm
6+
features:
7+
- agent-thought
8+
- tool-call
9+
- multi-tool-call
10+
- stream-tool-call
11+
- vision
12+
model_properties:
13+
mode: chat
14+
context_size: 8000
15+
parameter_rules:
16+
- name: temperature
17+
use_template: temperature
18+
- name: top_p
19+
use_template: top_p
20+
- name: max_tokens
21+
use_template: max_tokens
22+
default: 1024
23+
min: 1
24+
max: 8000
25+
- name: enable_enhance
26+
label:
27+
zh_Hans: 功能增强
28+
en_US: Enable Enhancement
29+
type: boolean
30+
help:
31+
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
32+
en_US: Allow the model to perform external search to enhance the generation results.
33+
required: false
34+
default: true
35+
pricing:
36+
input: '0.08'
37+
output: '0.08'
38+
unit: '0.001'
39+
currency: RMB

0 commit comments

Comments
 (0)