tloen alpaca-lora issues

tloen / alpaca-lora

Instruct-tune LLaMA on consumer hardware

Apache License 2.0

18.66k stars 2.22k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

RuntimeError: "normal_kernel_cpu" not implemented for 'Char'

#631 Parkourer10 closed 1 month ago
0
benchmark: add benchmark for alpaca lora

#630 zeroorhero opened 3 months ago
0
train: add benchmark metrics

#629 zeroorhero opened 3 months ago
0
InvalidHeaderDeserialization

#628 liuting20 opened 4 months ago
0
Why this error？ ValueError: We need an `offload_dir` to dispatch this model according to this `device_map`, the following submodules need to be offloaded: base_model.model.model.layers.3, base_model.model.model.layers.4, base_model.model.model.layers.5, base_model.model.model.layers.6, base_model.model.model.layers.7, base_model.model.model.layers.8, base_model.model.model.layers.9, base_model.model.model.layers.10, base_model.model.model.la

#627 hzbhh opened 6 months ago
0
Single GPU vs multiple GPUs stack (parallel)

#626 fdm-git opened 8 months ago
0
decapoda-research/llama-7b-hf is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

#625 Aekansh-Ak opened 8 months ago
2
Finetune scenarios

#624 Aekansh-Ak opened 8 months ago
0
0223 webfix

#623 niu769584641 closed 9 months ago
0
tag: llama2-7b-hf

#622 niu769584641 closed 9 months ago
0
failed to run on colab: ModulesToSaveWrapper has no attribute `embed_tokens`

#621 Vostredamus opened 9 months ago
0
Is there a way to check if this training is all done?

#620 OfficerChul opened 9 months ago
0
Is it possible to combine alpaca-lora with RAG

#619 HelloWorldLTY opened 9 months ago
0
Fix the IndexError in get_response

#618 RenzeLou opened 9 months ago
0
Loading a quantized checkpoint into non-quantized Linear8bitLt is not supported

#617 AngelMisaelPelayo opened 9 months ago
0
TensorRT - TensorRT - Complete RoPE & repeat_KV implementation.

#616 HengJayWang opened 10 months ago
0
LAION Open Assistant data is already released

#615 johnnynoone opened 10 months ago
0
Fix Dockerfile Missing Scipy Installation

#612 OliverGrace opened 11 months ago
0
The weights are not updated

#611 randomx207 opened 11 months ago
1
generate error after hit submit btn

#610 Minimindy opened 12 months ago
0
safetensors_rust.SafetensorError: Error while deserializing header: InvalidHeaderDeserialization

#609 mj2688 opened 12 months ago
15
Errors of tuning on 70B LLAMA 2, does alpaca-lora support 70B llama 2 tuning work?

#608 bqflab opened 1 year ago
0
is there any flag to mark the model is safetensors or pickle format?

#607 Tasarinan opened 1 year ago
0
When I set load_in_8bit=true, some errors occurred....

#606 hychaochao opened 1 year ago
0
AttributeError: module 'gradio' has no attribute 'inputs'

#605 Wenzhi-Ding opened 1 year ago
19
Load_in_8bit causing issues: Out of memory error with 44Gb VRAM in my GPU or device_map error

#604 Nimisha-Pabbichetty opened 1 year ago
1
can't load tokenizer

#603 Guo-Chenxu opened 1 year ago
2
generate error

#602 hychaochao closed 1 year ago
1
Are the saved models (either adapter_model.bin or pytorch_model.bin) only 25-26MB in size?

#601 LAB-703 opened 1 year ago
5
Error when loading lora weights

#600 kelsey-um closed 1 year ago
2
CUDA out of memory : I am using Colab T4 GPU

#599 anshumansinha16 opened 1 year ago
2
decapoda-research/llama-7b-hf no longer accessible

#598 mabreyes opened 1 year ago
5
Fix saved_pretrained saves empty adapter for new PEFT version. - Update finetune.py

#597 Marvinmw closed 7 months ago
0
load_dataset error with Kaggle environment

#596 TrieuLe0801 opened 1 year ago
0
Cannot backpropagate on the loss

#595 ajsanjoaquin opened 1 year ago
1
May I ask if this project supports internlm

#594 venxzw opened 1 year ago
0
No output when running generate.py

#593 vifi2021 closed 1 year ago
0
Fix incompatibility with newer transformers versions

#591 almogtavor opened 1 year ago
0
RuntimeError: shape '[32, 2, 64, 4096]' is invalid for input of size 26214400

#590 yourtiger closed 1 year ago
1
Possible bugs when using generate_response for batched inference

#589 binhmed2lab opened 1 year ago
0
File "/usr/local/lib/python3.10/dist-packages/torch/serialization.py", line 1033, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '<'.

#588 jacolamanna opened 1 year ago
1
Please update the template for Llama-2 chat completion

#587 binhmed2lab opened 1 year ago
1
i want to know how to not to use the wandb tool at the finetune.py

#586 BBaekdabang closed 1 year ago
0
Fine-tune argument resume_from_checkpoint starts from scratch instead of from checkpoint

#585 prpercival opened 1 year ago
1
GPU UTIL fluctuates wildly

#584 ssocean opened 1 year ago
1
How to control the save path of downloaded files

#583 lanyunzhu99 closed 1 year ago
0
All adapter_model.bin is the same

#581 paulthewineguy opened 1 year ago
2
Unable to determine this model’s pipeline type. Check the docs -- Huggingface Inference

#579 JonathanBechtel opened 1 year ago
1
lora for text classification

#578 paulthewineguy opened 1 year ago
0
[Question] about pipeline for fine-tuning with conversational question answering dataset.

#577 phamkhactu opened 1 year ago
0