Improve and re-release chapter 2 #911
Conversation
| } | ||
| ]} | ||
| /> | ||
| # Optimized Inference Deployment |
There was a problem hiding this comment.
There is an issue in the building process. I think it comes from the framework s tags in this file. I think at least is missing <FrameworkSwitchCourse {fw} />
|
|
||
| The model can be used in this state, but it will output gibberish; it needs to be trained first. We could train the model from scratch on the task at hand, but as you saw in [Chapter 1](/course/chapter1), this would require a long time and a lot of data, and it would have a non-negligible environmental impact. To avoid unnecessary and duplicated effort, it's imperative to be able to share and reuse models that have already been trained. | ||
| You'll notice that the tokenizer has added special tokens — `[CLS]` and `[SEP]` — required by the model. Not all models need special tokens; they're utilized when a model was pretrained with them, in which case the tokenizer needs to add them as that model expects these tokens. |
There was a problem hiding this comment.
This sentence feels convoluted
|
Super well written and informative, as always @burtenshaw. Great improvement over the previous iteration! Main issue is the failing build process. Rest are just nits 😄 |
Thanks @sergiopaniego . Working on the framework options now. |
Co-authored-by: Sergio Paniego Blanco <[email protected]>
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Co-authored-by: Sergio Paniego Blanco <[email protected]>
Co-authored-by: Sergio Paniego Blanco <[email protected]>
Co-authored-by: Sergio Paniego Blanco <[email protected]>
Co-authored-by: Sergio Paniego Blanco <[email protected]>
This is a minor improvement to chapter 2 to do these things: