Logo Questions Linux Laravel Mysql Ubuntu Git Menu
 

New posts in huggingface-transformers

How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?

How to use Huggingface Trainer with multiple GPUs?

Transformers PreTrainedTokenizer add_tokens Functionality

Using HuggingFace pipeline on pytorch mps device M1 pro

Why does the ProtBERT model generate identical embeddings for all non-whitespace-separated (single token?) inputs?

How to install pip install torch==2.1.2+cu118 in linux?

what is the difference between len(tokenizer) and tokenizer.vocab_size

The last dimension of the inputs to a Dense layer should be defined. Found None. Full input shape received: <unknown>

How can I make sentence-BERT throw an exception if the text exceeds max_seq_length, and what is the max possible max_seq_length for all-MiniLM-L6-v2?

Huggingface MarianMT translators lose content, depending on the model

How to efficiently mean-pool BERT embeddings while excluding padding?

HuggingFace's linear scheduler with warmup parameters

Tokenizer.from_file() HUGGINFACE : Exception: data did not match any variant of untagged enum ModelWrapper

Input type into Linear4bit is torch.float16, but bnb_4bit_compute_type=torch.float32 (default). This will lead to slow inference or training speed

How to Load a 4-bit Quantized VLM Model from Hugging Face with Transformers?

Loading checkpoint shards takes too long

Huggingface AutoTokenizer can't load from local path

what is so special about special tokens?

Transformers pretrained model with dropout setting