[go: up one dir, main page]
Skip to content

Issues: yuhuixu1993/qa-lora

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

23 Open 13 Closed
23 Open 13 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Trainig Process
#40 opened Nov 2, 2024 by z7r7y7
Whether the quantization model can support cpu inference
#39 opened Oct 24, 2024 by z7r7y7
is that right? could you tell me how to fix this error?
#36 opened May 28, 2024 by LiZhangMing
2
Merging problem
#35 opened May 28, 2024 by samuelqy
10
Thanks for your helpful project,could you give us model checkpoint as shown in figure
#33 opened May 21, 2024 by LiZhangMing
2
AWQ+LoRA available?
#32 opened Apr 15, 2024 by RanchiZhao
ValueError: Target modules [] not found in the base model.
#29 opened Mar 26, 2024 by akkkb
2
cannot reproduce the MMLU accuracy claimed in paper, could you release the script?
#28 opened Mar 23, 2024 by wenjingk-xilinx
4
3bit not supported by autogptq with triton?
#27 opened Mar 22, 2024 by wenjingk-xilinx
About the question of derivation of merge_with_quantization in the paper
#22 opened Jan 4, 2024 by LuletterSoul
1
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:3! (when checking argument for argument mat2 in method wrapper_CUDA_mm)
#21 opened Dec 30, 2023 by orangezfj
1
Finetuning Vision Foundation Models like OWL-ViT & Grounding Dino is possible? Any reference is available?
#20 opened Dec 21, 2023 by solomonmanuelraj
How to set batchsize
#18 opened Dec 7, 2023 by StiphyJay
1
Training with multi gpus, increase the batch size, and how to evaluate?
#17 opened Dec 5, 2023 by shawnricecake
5
The loss cannot converge when finetuning Llama2-7b-GPTQ on 4090
#16 opened Nov 30, 2023 by cyita
11
merge err: scales and qzeros dimension mismatch
#15 opened Nov 29, 2023 by sscheng216
4
How to support FLAN v2 dataset.
#14 opened Nov 24, 2023 by ChenMnZ
quantize_config.json file
#13 opened Oct 10, 2023 by thi3nnq
1
Adapter dimensions question
#12 opened Oct 6, 2023 by sparverius
4
RuntimeError: self and mat2 must have the same dtype
#10 opened Oct 3, 2023 by M-Elfeki
6
Is it possible to use an open source model that Huggingface has quantified？
#8 opened Oct 3, 2023 by wangxiaochun520
1
(Enhancement) Suggestion to incorporate GPTQ adapter merging into axolotl library
#7 opened Oct 3, 2023 by jaredquekjz
1
The paper is using Sum Pooling but the script is using Average Pooling
#5 opened Oct 2, 2023 by fahadh4ilyas
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.