explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-29 02:34:08 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix references to TransformerListener

Browse Source
This commit is contained in:
svlandeg 2020-08-27 14:33:28 +02:00
parent 4d37ac3f33
commit 28e4ba7270
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
website/docs/usage/embeddings-transformers.md
View File

@ -429,7 +429,7 @@ The same idea applies to task models that power the **downstream components**.
Most of spaCy's built-in model creation functions support a `tok2vec` argument, Most of spaCy's built-in model creation functions support a `tok2vec` argument,
which should be a Thinc layer of type ~~Model[List[Doc], List[Floats2d]]~~. This which should be a Thinc layer of type ~~Model[List[Doc], List[Floats2d]]~~. This
is where we'll plug in our transformer model, using the is where we'll plug in our transformer model, using the
[Tok2VecListener](/api/architectures#Tok2VecListener) layer, which sneakily [TransformerListener](/api/architectures#TransformerListener) layer, which sneakily
delegates to the `Transformer` pipeline component. delegates to the `Transformer` pipeline component.
```ini ```ini
@ -445,14 +445,14 @@ maxout_pieces = 3
use_upper = false use_upper = false
[nlp.pipeline.ner.model.tok2vec] [nlp.pipeline.ner.model.tok2vec]
@architectures = "spacy-transformers.Tok2VecListener.v1" @architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0 grad_factor = 1.0
[nlp.pipeline.ner.model.tok2vec.pooling] [nlp.pipeline.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1" @layers = "reduce_mean.v1"
``` ```
The [Tok2VecListener](/api/architectures#Tok2VecListener) layer expects a The [TransformerListener](/api/architectures#TransformerListener) layer expects a
[pooling layer](https://thinc.ai/docs/api-layers#reduction-ops) as the argument [pooling layer](https://thinc.ai/docs/api-layers#reduction-ops) as the argument
`pooling`, which needs to be of type ~~Model[Ragged, Floats2d]~~. This layer `pooling`, which needs to be of type ~~Model[Ragged, Floats2d]~~. This layer
determines how the vector for each spaCy token will be computed from the zero or determines how the vector for each spaCy token will be computed from the zero or