-
### Description
EVAL && EVALSHA commands infers wrong node by key hash slot on cluster mode.
Usage in abstract:
```js
const sha = /** sha of script that get some key */
const keys = ['1key']
c…
-
### Describe the issue
I'm unable to convert [this model](https://huggingface.co/hf-internal-testing/tiny-random-MusicgenForConditionalGeneration) to fp16 to be used with transformers.js
I've al…
-
### Feature request
Hi, I've created a 4-bit quantized model using `BitsAndBytesConfig`, for example
```
from transformers import AutoModelForTokenClassification, BitsAndBytesConfig
from optim…
-
### Question
Hello, Greetings Vladimir, programmer in a web environment with PHP, JS, AJAX, first I apologize for my English, my native language is Latin Spanish, I am not very good at writing it, I …
-
### Feature request
New feature using VAD for silence suppression. A better description can be found at https://github.com/jianfch/stable-ts?tab=readme-ov-file#silence-suppression
### Motivation…
-
Can't really tell where this error is coming from when running `node src/scripts/indexBlogLocal.mjs`. Is it failing to connect to supabase?
```
node:internal/deps/undici/undici:11576
Error.capt…
-
This commit removed `prepare_model_inputs`: https://github.com/xenova/transformers.js/commit/ebd533531a84ceb6db4fce5c39e7ae27f543aa05
Which breaks other projects, specifically:
https://github.co…
-
**Describe the bug**
This is an old bug (#1348 ), but it reappeared in version 0.49.16 again, when I try to enable monaco editor.
**Minimal reproduction**
Steps to reproduce the behav…
-
When optimizer used in conjuction together with optimizer-express it's not possible to pass params to optimizer's `transformHtml` method, only configuration to the optimizer constructor.
And while …
mk0x9 updated
4 years ago
-
### Feature request
As the vocabulary of newer models, like Llama 3 or Gemma, increases in size, so does the size of the tokenizer, which includes the vocabulary as JSON (and merges for BPE tokenizer…