SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[chat] generate parameterization powered by GenerationConfig and UX-related changes (#38047)

Browse Source 
* accept arbitrary kwargs

* move user commands to a separate fn

* work with generation config files

* rm cmmt

* docs

* base generate flag doc section

* nits

* nits

* nits

* no <br>

* better basic args description
This commit is contained in:
Joao Gante
2025-05-12 14:04:41 +01:00
committed by GitHub
parent a5c6172c81
commit 8efe3a9d77
4 changed files with 326 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/source/en/conversations.md
View File

@@ -27,7 +27,7 @@ This guide shows you how to quickly start chatting with Transformers from the co
## transformers CLI
Chat with a model directly from the command line as shown below. It launches an interactive session with a model. Enter `clear` to reset the conversation, `exit` to terminate the session, and `help` to display all the command options.
After you've [installed Transformers](./installation.md), chat with a model directly from the command line as shown below. It launches an interactive session with a model, with a few base commands listed at the start of the session.
```bash
transformers chat Qwen/Qwen2.5-0.5B-Instruct
@@ -37,6 +37,12 @@ transformers chat Qwen/Qwen2.5-0.5B-Instruct
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/transformers-chat-cli.png"/>
</div>
You can launch the CLI with arbitrary `generate` flags, with the format `arg_1=value_1 arg_2=value_2 ...`
```bash
transformers chat Qwen/Qwen2.5-0.5B-Instruct do_sample=False max_new_tokens=10
```
For a full list of options, run the command below.
```bash