|
Tokenizer.add_tokens automatically convert ESM2 new token to special
|
|
1
|
355
|
January 8, 2024
|
|
Is it possible to finetune *ForQA models with SFT (PEFT/QLoRA)?
|
|
2
|
577
|
January 7, 2024
|
|
Huggingface Question Answering on bert Validation on Squad (list index out of range())
|
|
0
|
196
|
January 7, 2024
|
|
Extremly long runtime with Trainer.push_to_hub() without error
|
|
0
|
137
|
January 7, 2024
|
|
Layoutlmv2 inferencing google colab notebook
|
|
0
|
159
|
January 6, 2024
|
|
Using the Hugging face hosting
|
|
0
|
165
|
January 6, 2024
|
|
Can't install torch
|
|
0
|
349
|
January 6, 2024
|
|
British English TTS model
|
|
0
|
153
|
January 6, 2024
|
|
Distillation for LongT5
|
|
0
|
193
|
January 6, 2024
|
|
Text-To-Image model not connecting in google Colab
|
|
0
|
615
|
November 28, 2023
|
|
Interect with existing chat module
|
|
0
|
115
|
January 5, 2024
|
|
Empty BERT Model, any help?
|
|
2
|
499
|
January 5, 2024
|
|
Anywhere where I can read more about the `device_map` kwarg in `from_pretrained`?
|
|
2
|
14757
|
January 5, 2024
|
|
How to use LLMs like LLAMA-2 for NER tasks?
|
|
0
|
1209
|
January 4, 2024
|
|
Learining rate is zero for a 1.5 epocs
|
|
0
|
158
|
January 3, 2024
|
|
Text generation model returns an error on Spaces
|
|
0
|
142
|
January 3, 2024
|
|
Speculative Decoding: How to verify multiple tokens in a single forward pass?
|
|
0
|
347
|
January 4, 2024
|
|
Langchain and streamlit chatbot
|
|
0
|
1525
|
January 3, 2024
|
|
Which models should I use for image colourisation and enhancement
|
|
1
|
428
|
January 3, 2024
|
|
How to calculate word and sentence embedding using GPT-2?
|
|
0
|
633
|
January 3, 2024
|
|
Performance of mtb-7b on mac M1
|
|
0
|
1283
|
January 3, 2024
|
|
Autotrain fine tune error - trains only first 3 data sets
|
|
0
|
410
|
January 2, 2024
|
|
How to show the learning rate during training
|
|
12
|
4067
|
January 2, 2024
|
|
Confusing (and possibly misleading) PPO Trainer Code from TRL API Doc Tutorial
|
|
2
|
475
|
January 2, 2024
|
|
Can we use a model hosted on another platform (for example banana.dev) to run hugging face's perplexity metric on?
|
|
0
|
232
|
January 2, 2024
|
|
Trainer's `save_model` isn't saving the entire state_dict and is only saving the embedding/encoder
|
|
1
|
1557
|
January 2, 2024
|
|
Accessing logits when using Trainer API
|
|
1
|
331
|
January 1, 2024
|
|
Continue pretraining on a released model
|
|
0
|
810
|
January 1, 2024
|
|
Training Uncensored AI w/ My Data Set
|
|
0
|
727
|
January 1, 2024
|
|
Create custom character
|
|
0
|
200
|
January 1, 2024
|