sgpt

sgpt copied to clipboard

Davidtverd

Usage for semantic search

6

Hello, I want to create a semantic search functionality. The model is accurate in calculating the similarity between the word synonyms. Here are a few excerpts of the demo: Supposedly,...

rut00

Usage for text-2-text-generation

1

I am relatively new to using Hugging Face models. I found this model and I think that it may work well with my use case which is to create a...

shafkat-07

Could I fine tune this model for Chinese datasets?

11

Could you please tell me how i can fine tune for my custom Chinese datasets?

asenasen123

HuggingFace script and Sentence Transformers script giving different results

2

I copy-pasted the two scripts [0][1] into a notebook without any changes. They produce different embeddings and different results. HG gives: `Cosine similarity between "I'm searching for a planet not...

vladkvit

Could I change the max_seq_length?

3

I need to input a length greater than the maximum sequence length.Could I need change the max_seq_length?

asenasen123

Fine-tune Muennighoff/SGPT-2.7B-weightedmean-msmarco-specb-bitfit using TSDAE approach

4

Hi, I am trying to fine-tune SGPT-2.7B-weightedmean-msmarco-specb-bitfit with unlabeled dataset using TSDAE approach. Getting this error: Type Error: forward() got an unexpected keyword argument 'encoder_hidden_states'. Please help. Thanks! Stack Trace:...

BalajiAJ

Error when using sentence_transformer

15

When I run: ```model = SentenceTransformer("Muennighoff/SGPT-125M-weightedmean-nli-bitfit")``` the following error happens: ```TypeError: Pooling.__init__() got an unexpected keyword argument 'pooling_mode_weightedmean_tokens'```. My machine: - OS: MacOs, chip M1 - pytorch: 1.12.1 - sentence_transformer:...

TamHHM

If I input more than the max_seq_length？

4

I see that sgpt-bloom-7b1-mamarco model has a vector length of 300，but If I input more than the maximum length, for example, input more than 400 Chinese characters, it seems that...

runwean

How to fine tune on my datasets

8

Can you please share how i can finetune for my custom domain datasets?

shaileshj2803