TechQA.

Question

What is the difference between PEFT and RAFT?

score 21 · Answer 1 · 2024-03-27T05:08:35.310000

0

Answer

21

Views

What is the difference between PEFT and RAFT?

21 views Asked by Krishna At 27 March 2024 at 05:08

score 29 · Answer 2 · 2024-03-26T16:07:17.277000

Accuracy at 0 during inference with peft and Vision EncoderDecoderModel from huggingface

29 views Asked by user21970358 At 26 March 2024 at 16:07

score 589 · Answer 3 · 2024-03-23T16:05:27.167000

PyTorch: AttributeError: 'torch.dtype' object has no attribute 'itemsize'

589 views Asked by Lidor Eliyahu Shelef At 23 March 2024 at 16:05

score 36 · Answer 4 · 2024-03-22T16:12:41.390000

Repo id must use alphanumeric chars : while performing auto training on llm

36 views Asked by Ankur Kumar At 22 March 2024 at 16:12

score 81 · Answer 5 · 2024-03-07T16:34:03.633000

Struggling with Hugging Face PEFT

81 views Asked by countermode At 07 March 2024 at 16:34

score 29 · Answer 6 · 2024-03-06T13:12:37.957000

What is the difference between merging LORA weight with base model and not merging the weight in LLAMA2 (LLM)?

29 views Asked by XGB At 06 March 2024 at 13:12

score 225 · Answer 7 · 2024-03-05T13:03:24.453000

'MistralForCausalLM' object has no attribute 'merge_and_unload"

225 views Asked by NetForceProduction At 05 March 2024 at 13:03

score 77 · Answer 8 · 2024-02-22T18:09:37.907000

convert a PeftModel back to the original model but with updated weights

77 views Asked by afsara_ben At 22 February 2024 at 18:09

score 79 · Answer 9 · 2024-02-22T02:38:19.443000

finetune a model with LoRa, then load it in its vanilla architecture

79 views Asked by afsara_ben At 22 February 2024 at 02:38

score 34 · Answer 10 · 2024-02-21T23:17:04.797000

how to save adapter.bin model as .pt model

34 views Asked by afsara_ben At 21 February 2024 at 23:17

score 498 · Answer 11 · 2024-02-21T04:11:21.533000

How to resolve ValueError: You should supply an encoding or a list of encodings to this method that includes input_ids, but you provided ['label']

498 views Asked by tlanigan At 21 February 2024 at 04:11

score 104 · Answer 12 · 2024-02-16T15:16:40.707000

Resume training from a checkpoint with different hyperparameters when training with PEFT and transformers

104 views Asked by Jon Flynn At 16 February 2024 at 15:16

score 259 · Answer 13 · 2024-02-16T14:39:55.417000

Huggingface transformer train function throwing Device() received an invalid combination of arguments

259 views Asked by Syed Mohammad Fahim Abrar At 16 February 2024 at 14:39

score 60 · Answer 14 · 2024-02-15T15:44:50.560000

Why no log for training model, and key_error for 'eval_loss'?

60 views Asked by Therrief At 15 February 2024 at 15:44

score 138 · Answer 15 · 2024-02-14T04:19:13.777000

How do I save a huggingface LLM model into shards?

138 views Asked by Muhammad Omar Farooq At 14 February 2024 at 04:19

score 193 · Answer 16 · 2024-02-06T15:20:29.300000

Running out of memory during PEFT LoRA fine-tuning of LLMs with 7B parameters

193 views Asked by Sebastian Simon At 06 February 2024 at 15:20

score 47 · Answer 17 · 2024-01-31T03:05:13.573000

using peft after bits and bytes seems to have no effect on LLM

47 views Asked by user3476463 At 31 January 2024 at 03:05

score 37 · Answer 18 · 2024-01-25T21:37:31.133000

OSError: ./peft-dialogue-summary-checkpoint-local does not appear to have a file named config.json

37 views Asked by ZandaJr At 25 January 2024 at 21:37

score 29 · Answer 19 · 2024-01-22T16:27:45.910000

padding_idx or self.num_embeddings gets changed into a string while finetuning Llama 2

29 views Asked by sanminchui At 22 January 2024 at 16:27

score 114 · Answer 20 · 2024-01-11T19:53:19.200000

Is it possible to fine tune the model nllb200_1.3B in Google Colab?

114 views Asked by Maximiliano Ramirez At 11 January 2024 at 19:53

TechQA.

List Question

What is the difference between PEFT and RAFT?

Accuracy at 0 during inference with peft and Vision EncoderDecoderModel from huggingface

PyTorch: AttributeError: 'torch.dtype' object has no attribute 'itemsize'

Repo id must use alphanumeric chars : while performing auto training on llm

Struggling with Hugging Face PEFT

What is the difference between merging LORA weight with base model and not merging the weight in LLAMA2 (LLM)?

'MistralForCausalLM' object has no attribute 'merge_and_unload"

convert a PeftModel back to the original model but with updated weights

finetune a model with LoRa, then load it in its vanilla architecture

how to save adapter.bin model as .pt model

How to resolve ValueError: You should supply an encoding or a list of encodings to this method that includes input_ids, but you provided ['label']

Resume training from a checkpoint with different hyperparameters when training with PEFT and transformers

Huggingface transformer train function throwing Device() received an invalid combination of arguments

Why no log for training model, and key_error for 'eval_loss'?

How do I save a huggingface LLM model into shards?

Running out of memory during PEFT LoRA fine-tuning of LLMs with 7B parameters

using peft after bits and bytes seems to have no effect on LLM

OSError: ./peft-dialogue-summary-checkpoint-local does not appear to have a file named config.json

padding_idx or self.num_embeddings gets changed into a string while finetuning Llama 2

Is it possible to fine tune the model nllb200_1.3B in Google Colab?

Popular Questions

Trending Questions