issues
search
artidoro
/
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
https://arxiv.org/abs/2305.14314
MIT License
10.06k
stars
822
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to implement normal float NF4?
#299
XA23i
opened
4 days ago
0
llama 3 8b results
#298
dorsa-zeinali
opened
2 months ago
0
反向传播时，梯度是如何计算的
#297
21-10-4
opened
4 months ago
0
llama 3 -support?
#296
LuoyaoChen
opened
5 months ago
0
additional load_in_4bit removed
#295
shirinyamani
opened
5 months ago
0
Qlora with flan-t5 issue - ValueError: Trying to set a tensor of shape torch.Size([4096, 4096])
#294
JhonDan1999
opened
5 months ago
0
Paged optimizer vs gradient checkpointing?
#293
LeoPerelli
opened
6 months ago
0
Error when loading model
#292
m000lie
opened
6 months ago
3
Llama 1 7b MMLU results largely diverges from reported
#291
Edenzzzz
opened
7 months ago
0
a critical loss drop happen after each epoch ending
#290
Coco58323
opened
7 months ago
0
Question about deployment of fine tuned model
#289
Brandon371
opened
8 months ago
0
Fuyu-8B qLora
#288
SinanAkkoyun
opened
9 months ago
0
RuntimeError: expected mat1 and mat2 to have the same dtype, but got: float != c10::BFloat16
#287
andeyeluguo
closed
9 months ago
1
[Questions]: How to implement NF4/NF2 matmul kernel function?
#286
llCurious
opened
10 months ago
2
Table 4 and Table 5 have different results
#285
lemyx
opened
10 months ago
0
[Bug] large CUDA memory usage in the evaluation phase
#284
ChenMnZ
opened
10 months ago
1
How to support FLAN v2 dataset.
#283
ChenMnZ
opened
11 months ago
0
How do you use oasst1 dataset in qlora.py - why only the 'text' field is used?
#282
Huxwell
opened
11 months ago
0
Using QLORA for Multi Modal Vison Foundation Models Optimization - google/owlv2-base-patch16-ensemble
#281
solomonmanuelraj
opened
11 months ago
0
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED when calling `cublasCreate(handle)`
#280
Juanerx
opened
11 months ago
1
Issue with Yi 34B Training EOS token not working
#279
mrmuke
closed
11 months ago
1
Saving/Loading qlora adapters
#278
chrisi2045
opened
12 months ago
1
Merge issue
#277
qburst-fidha
opened
1 year ago
0
Multi-GPU Training Giving Different Loss
#276
nikhil-ghosh-berkeley
opened
1 year ago
1
Unable to generate predictions
#275
SamarthMM
opened
1 year ago
0
Garbage output of Llama-2-13B-chat model after qlora finetuning
#274
cywsg
opened
1 year ago
0
Quantization aware finetuning?
#273
SinanAkkoyun
opened
1 year ago
0
Qlora Read me fix
#272
Vezora-Corp
opened
1 year ago
0
Training on logits rather than tokens?
#271
SinanAkkoyun
opened
1 year ago
0
adding lba support for qlora
#270
itayhubara
closed
1 year ago
0
extra memory usage for loading the model
#269
XintianHan
opened
1 year ago
0
TypeError: 'NoneType' object is not iterable
#268
reilgun
opened
1 year ago
3
DDP Training fails
#267
AntoineBlanot
closed
1 year ago
1
[XPU] CUDA error when running on arc770 with Intel extension for pytorch
#266
delock
opened
1 year ago
1
can we only evaluate the mmlu_dataset when sh sh scripts/finetune_guanaco_7b.sh?
#265
LiZhangMing
opened
1 year ago
1
Could not reproduce the results listed in your paper using a single 3090 card.
#264
LiZhangMing
opened
1 year ago
6
[Bug Fix] Add importing `warnings`
#263
tongyx361
opened
1 year ago
0
uneven distribution of GPU workload
#262
liatamax
opened
1 year ago
1
Question: CUDA memory usage in the evaluation phase
#261
LimboWK
opened
1 year ago
2
Why do we print just half of `trainable_params" when using 4-bits?
#260
HanGuo97
opened
1 year ago
0
[Question] Why can we set `model_parallel` and `is_parallelizable` to `True` for whichever `model`?
#259
tongyx361
opened
1 year ago
0
Why do we need the Dequantization process?
#258
nthehai01
opened
1 year ago
0
Fix outdated description of HF arguments in README.md
#257
tongyx361
opened
1 year ago
0
Error invalid device ordinal at line 393
#255
matt-seb-ho
opened
1 year ago
0
Should base model be dequantized when merging LoRA weights with base model?
#254
jinyongyoo
opened
1 year ago
6
Getting error dataclasses.FrozenInstanceError: cannot assign to field generation_config when executing any of the scripts in the scripts folder with default parameters.
#253
vasuems
opened
1 year ago
2
epoch presented does not match the calculation
#252
lijierui
opened
1 year ago
0
[Bug] Test set is taken from training set
#251
Peter-Devine
opened
1 year ago
1
can be used in stable diffusion?
#250
henbucuoshanghai
opened
1 year ago
0
curious about the train speed
#249
JustQJ
opened
1 year ago
0
Next