Skip to content

Commit b213e63

Browse files
authored
Merge pull request d-run#387 from windsonsea/story
[en] Update terms: model gallery, playground, served models
2 parents 012279e + 08ca896 commit b213e63

File tree

5 files changed

+32
-32
lines changed

5 files changed

+32
-32
lines changed

docs/zh/docs/en/models/deploy.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -3,15 +3,15 @@ hide:
33
- toc
44
---
55

6-
# Deploy a Model
6+
# Serve a Model
77

8-
You can deploy models from the **Model Store** or **Model Services**. Below are the details for configuring the deployment:
8+
You can serve models from the **Model Gallery** or **Served Models**. Below are the details for serving a model:
99

10-
![deploy](./images/deploy01.png)
10+
![Serving](./images/deploy01.png)
1111

1212
- **Select the Model**
1313

14-
Choose the model to deploy (e.g., Qwen2-0.5B-Instruct), ensuring it aligns with your business needs and task requirements.
14+
Choose the model to serve (e.g., Qwen2-0.5B-Instruct), ensuring it aligns with your business needs and task requirements.
1515

1616
- **Model Service Name Requirements**
1717
The name of the model service must meet the following criteria:
@@ -22,11 +22,11 @@ You can deploy models from the **Model Store** or **Model Services**. Below are
2222

2323
- **Region**
2424

25-
Select the region for service deployment (e.g., "Shanghai Area 2"). Choose a region based on your business coverage and latency needs.
25+
Select the region for serving (e.g., "Shanghai Area 2"). Choose a region based on your business coverage and latency needs.
2626

2727
- **Number of Instances**
2828

29-
- Configure the number of instances to deploy. Default value: 1.
29+
- Configure the number of instances to serve. Default value: 1.
3030
- More instances enhance service concurrency, but they will also increase costs.
3131

3232
- **Billing Method**

docs/zh/docs/en/models/exp.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
# Try a Model
1+
# Playground
22

33
d.run offers most models not only with the ability to view documentation but also with an interactive inference experience. For example, you can engage in daily chats with large language models to intuitively explore their capabilities.
44

@@ -8,12 +8,12 @@ d.run offers most models not only with the ability to view documentation but als
88

99
The platform provides two entry points, allowing you to choose based on your needs.
1010

11-
- **Entry 1** : On the [Model Store](./index.md) page, select your preferred model and click **Use Model** to enter the chat page.
12-
- **Entry 2** : From the left-side menu, click **Use Model** to directly start the model experience process.
11+
- **Entry 1** : On the [Model Gallery](./index.md) page, select your preferred model and click **Playground** to enter the chat page.
12+
- **Entry 2** : From the left-side menu, click **Playground** to directly start the model experience process.
1313

1414
## Instructions
1515

16-
Upon your first visit to the **Use Model** , the system will recommend some popular and high-quality models for you to try. You can:
16+
Upon your first visit to the **Playground** , the system will recommend some popular and high-quality models for you to try. You can:
1717

1818
- Click on a recommended model to directly use the chat functionality of the large language model.
1919
- Or choose from the list of other models you’re interested in.

docs/zh/docs/en/models/index.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -3,13 +3,13 @@ hide:
33
- toc
44
---
55

6-
# Model Store
6+
# Model Gallery
77

8-
The Model Store offers a diverse selection of models covering areas such as text generation, image understanding, and speech synthesis. It integrates hundreds of models from providers like Tongyi Qianwen, Mistral, Meta, Cohere, and more. Users can flexibly deploy models according to their business needs to achieve efficient real-time inference.
8+
The Model Gallery offers a diverse selection of models covering areas such as text generation, image understanding, and speech synthesis. It integrates hundreds of models from providers like Tongyi Qianwen, Mistral, Meta, Cohere, and more. Users can flexibly serve models according to their business needs to achieve efficient real-time inference.
99

1010
## Find a model
1111

12-
Using the tags in the Model Store, you can quickly search the model list, supporting multiple tag selections, and you can clear the filter conditions at any time.
12+
Using the tags in the Model Gallery, you can quickly search the model list, supporting multiple tag selections, and you can clear the filter conditions at any time.
1313

1414
![find](./images/exper00.png)
1515

@@ -28,9 +28,9 @@ In the upper right corner of the chat window, click **Change Model** to choose d
2828

2929
![Experience](./images/exper02.png)
3030

31-
## Deploy a Model
31+
## Serve a Model
3232

33-
You can easily deploy models from the **Model Store** or **Model Service** pages.
34-
Refer to [Deployment Parameters](./deploy.md).
33+
You can easily serve models from the **Model Gallery** or **Model Service** pages.
34+
Refer to [Serving Parameters](./deploy.md).
3535

3636
[Register and Try d.run](https://console.d.run/){ .md-button .md-button--primary }

docs/zh/docs/en/rel-notes.md

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -37,10 +37,10 @@ This page outlines key feature updates for **d.run** .
3737

3838
### LLM Studio v0.5.0
3939

40-
- [Model Store] Added support for "Deep Thinking" in text models
41-
- [Model Store] Enabled message copying and regeneration for text models
42-
- [Model Store] Image-to-text models can now generate multiple images simultaneously
43-
- [Model Store] Image-to-text models now support custom positive/negative prompts and image sizes
40+
- [Model Gallery] Added support for "Deep Thinking" in text models
41+
- [Model Gallery] Enabled message copying and regeneration for text models
42+
- [Model Gallery] Image-to-text models can now generate multiple images simultaneously
43+
- [Model Gallery] Image-to-text models now support custom positive/negative prompts and image sizes
4444
- [Model Service] Fully compatible with the standard OpenAI SDK
4545
- [API Keys] Usage statistics can now be filtered by API key, model type, and invocation time
4646
- [API Keys] Quickly view total calls, total input tokens, and total output tokens
@@ -66,12 +66,12 @@ This page outlines key feature updates for **d.run** .
6666

6767
### LLM Studio v0.1.0
6868

69-
- [Model Store] Card view for model list for better visualization
70-
- [Model Store] Detailed model descriptions and API call examples
71-
- [Model Store] Quick deployment and testing of text models
72-
- [Model Store] Search models by name, provider, and type
73-
- [Model Store] Try multimodal models
74-
- [Model Store] Try image-to-text models
69+
- [Model Gallery] Card view for model list for better visualization
70+
- [Model Gallery] Detailed model descriptions and API call examples
71+
- [Model Gallery] Quick deployment and testing of text models
72+
- [Model Gallery] Search models by name, provider, and type
73+
- [Model Gallery] Try multimodal models
74+
- [Model Gallery] Try image-to-text models
7575
- [Model Service] View list of deployed model services
7676
- [Model Service] Variety of models available for deployment
7777
- [Model Service] Instance scaling support
@@ -80,9 +80,9 @@ This page outlines key feature updates for **d.run** .
8080
- [Model Service] Configure number of instances for horizontal scaling
8181
- [Model Service] In-browser experience of deployed models
8282
- [Model Service] API examples in multiple languages (curl, Python, Node.js)
83-
- [Use Model] One-click testing to quickly verify service availability
84-
- [Use Model] Text generation models support parameters like `system prompt`, `temperature`, and `top_p`
85-
- [Use Model] Compare different models of the same type
83+
- [Playground] One-click testing to quickly verify service availability
84+
- [Playground] Text generation models support parameters like `system prompt`, `temperature`, and `top_p`
85+
- [Playground] Compare different models of the same type
8686
- [API Keys] View API key list
8787
- [API Keys] One-click copy of full API key
8888
- [API Keys] Delete specific keys (irreversible)

docs/zh/navigation.yml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -150,10 +150,10 @@ plugins:
150150
容器实例开关机: Power on/off
151151
文件存储: File Storage
152152
大模型服务平台: LLM Studio
153-
模型广场: Model Store
154-
模型部署: Deploy Model
153+
模型广场: Model Gallery
154+
模型部署: Served Models
155155
模型服务: Model Service
156-
模型体验: Try a Model
156+
模型体验: Playground
157157
API Key 管理: API Keys
158158
AI 应用: AI Apps
159159
功能列表: Features

0 commit comments

Comments
 (0)