Eshan Chordia's picture

43

Eshan Chordia

eshanc

·

AI & ML interests

None yet

Organizations

New activity in mistralai/Mistral-7B-Instruct-v0.1 4 months ago

Error in loading completely fine-tuned (all 7B parameters updated)

#106 opened over 1 year ago by

When the length of prompt is larger than sliding_window = 4096, RuntimeError:

#128 opened about 1 year ago by

AttributeError, When using Specific GPU

#75 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 4 months ago

Error in accessing the hiddensize

#177 opened almost 2 years ago by

avinashmudireddy

New activity in mistralai/Mistral-7B-Instruct-v0.1 4 months ago

Which padding side to choose while finetuning

#47 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 4 months ago

Failed! Model mixtral-8x7b-instruct failed to start after update

#248 opened about 1 year ago by

Fine-tuning Mixtral with different types of datasets

#214 opened over 1 year ago by

Question on further fine-tuning

#40 opened about 2 years ago by

New activity in google/gemma-7b-it 4 months ago

ValueError: Trying to set a tensor of shape torch.Size([4096, 3072]) in "weight" (which has shape torch.Size([6291456, 1])), this look incorrect.

#81 opened almost 2 years ago by

Subhasisdasgupta

New activity in mistralai/Mistral-7B-Instruct-v0.1 4 months ago

Key Error

#9 opened over 2 years ago by

Finetuning using RayTrain

#83 opened about 2 years ago by

New activity in google/gemma-7b-it 4 months ago

Error while training gemma 7-b

#49 opened almost 2 years ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 4 months ago

KeyError: 'mixtral' even transformers is 4.36.2

#55 opened about 2 years ago by

New activity in mistralai/Mistral-7B-Instruct-v0.1 4 months ago

CUDA out of memory

#91 opened about 2 years ago by

logan39522361tq

error while running the model

#33 opened about 2 years ago by

Error with Tokenizer

#121 opened over 1 year ago by

New activity in google/gemma-7b-it 4 months ago

Finetuning data format (alpaca or chat)

#33 opened almost 2 years ago by

New activity in mistralai/Mistral-7B-Instruct-v0.1 4 months ago

401 Client Error: Unauthorized for url

#125 opened over 1 year ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 4 months ago

8bit quantization error

#98 opened almost 2 years ago by

New activity in google/gemma-7b-it 4 months ago

ValueError with multi A100 GPUS

#28 opened almost 2 years ago by