You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Generative models typically use external weights, so use the downloadOptions.ExternalDataPath option when downloading the model. See the [example](./testData/downloadModels.go) here.
220
+
Generative models typically use external weights, so use the downloadOptions.ExternalDataPath option when downloading the model. See the [example](testcases/downloadModels.go) here.
@@ -316,7 +316,7 @@ We is currently supported only for the **FeatureExtractionPipeline**. This can b
316
316
{"sentence1": "The quick brown fox jumps over the lazy dog", "sentence2": "A quick brown cow jumps over a lazy caterpillar", "score": 0.5}
317
317
```
318
318
319
-
See the [example](./testData/semanticSimilarityTest.jsonl) for a sample dataset.
319
+
See the [example](testcases/semanticSimilarityTest.jsonl) for a sample dataset.
320
320
321
321
The score is assumed to be a float between 0 and 1 that encodes the semantic similarity between the sentences, and by default a cosine similarity loss is used (see [sentence transformers](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss)). However, you can also specify a different loss function from `goMLX` using the `XLATrainingOptions` field in the `TrainingConfig` struct. See [the training tests](./hugot_training_test.go) for examples on how to train or fine-tune feature extraction pipelines.
0 commit comments