Buckets:

hf-doc-build/doc-dev / huggingface.js /pr_2407 /en /inference /interfaces /TextGenerationStreamPrefillToken.md
|
download
raw
933 Bytes
# Interface: TextGenerationStreamPrefillToken
## Properties
### id
**id**: `number`
Token ID from the model tokenizer
#### Defined in[[id.defined-in]]
[inference/src/tasks/nlp/textGenerationStream.ts:23](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGenerationStream.ts#L23)
___
### logprob
• `Optional` **logprob**: `number`
Logprob
Optional since the logprob of the first token cannot be computed
#### Defined in[[logprob.defined-in]]
[inference/src/tasks/nlp/textGenerationStream.ts:30](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGenerationStream.ts#L30)
___
### text
• **text**: `string`
Token text
#### Defined in[[text.defined-in]]
[inference/src/tasks/nlp/textGenerationStream.ts:25](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/textGenerationStream.ts#L25)

Xet Storage Details

Size:
933 Bytes
·
Xet hash:
d32206953732f454f595a6d357016d5667adb65faf1aee2dba211567b6d5952f

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.