Jegor Kitškerkin

@yongyi520 Magically, I have tried installing this library again (after almost half a year) and the problem got fixed by itself I can send you my dependencies and any other...

@yongyi520 yes, I am using M1, here is my full list of dependencies (I use pnpm) ``` "dependencies": { "@aws-sdk/client-s3": "^3.435.0", "@chakra-ui/icons": "^2.1.1", "@chakra-ui/react": "^2.8.1", "@emotion/cache": "^11.11.0", "@emotion/react": "^11.11.1", "@emotion/server":...

Hey @McPatate, thanks for your reply! here is the output of pickletools ``` 0: \x80 PROTO 4 2: \x95 FRAME 526 11: \x8c SHORT_BINUNICODE 'setfit.modeling' 28: \x94 MEMOIZE (as 0)...

The code that I have used: ```python from setfit import SetFitModel, SetFitTrainer from sentence_transformers.losses import CosineSimilarityLoss from datasets import Dataset dataset = Dataset.load_from_disk("dataset") label2id = { label: idx for idx,...

@McPatate @tomaarsen I think that using a different format for saving the head can also solve the problem that I have encountered here https://github.com/huggingface/setfit/issues/206 (not about moving between devices, but...

Update: it seems to be loading with 4 L4 GPUs and bitsandbytes quantization, but it takes like 2h of waiting (printing the "Waiting for shard to be ready..." message). What's...

I am experiencing a similar problem. Here is the generated code: ```typescript public static uploadFile(data: $OpenApiTs['/file/upload']['post']['req']): CancelablePromise { return __request(OpenAPI, { method: 'POST', url: '/file/upload', query: { table_name: data.tableName },...

hey @DrakkoFire I was facing a similar issue, I found a way to do it via the Dokploy API if you want, you can check out how I have imlpemented...

@LysandreJik I am getting the same error with 2.1.0 but not with 2.0.3 (running on T4) is there any way to disable flash attention?

@claudioMontanari indeed, the time per token is the same But setting the maximum number of tokens to 256 (for both endpoint calls) yields me same 0.3-0.4s and 1.8s-1.9s latency