Skip to content

Issues: unslothai/unsloth

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

509 Open 497 Closed
509 Open 497 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

Low GPU utilization when running Unsloth-finetuned Qwen2.5-Coder-14B-Instruct-128K-GGUF
#1292 opened Nov 14, 2024 by e1ijah1
Extremely long context finetuning
#1291 opened Nov 14, 2024 by GianlucaDeStefano
Train on responses only does not seem to work for Mistral format
#1290 opened Nov 14, 2024 by LostRuins
unexpected keyword argument tokenizer [FIXED] fixed - pending confirmation Fixed, waiting for confirmation from poster
#1285 opened Nov 13, 2024 by avemio-digital
4
{% if add_generation_prompt %} [FIXED] fixed - pending confirmation Fixed, waiting for confirmation from poster
#1284 opened Nov 13, 2024 by giuliabaldini
2
Error loading model: Unsloth: unsloth/Meta-Llama-3.1-8B-bnb-4bit not supported yet! Make an issue to https://github.com/unslothai/unsloth!
#1283 opened Nov 13, 2024 by sree-tejis
3
Gradient norm is zero for training Qwen2.5-0.5B-Instruct in unsloth=="2024.11.6"
#1282 opened Nov 12, 2024 by joe32140
1
FileExistsError: [WinError 183]
#1279 opened Nov 12, 2024 by rogersohandsome
1
Will the open source version support multiple Gpus later?
#1278 opened Nov 12, 2024 by first-li
3
Can you support the fine-tuning of the MiniCPM3-4B model ?
#1277 opened Nov 12, 2024 by faceair
2
Finetuned Llama 3.1 8B (base) gets stuck in a loop
#1275 opened Nov 11, 2024 by skerit
2
Add Support for Pre-Training feature request Feature request pending on roadmap
#1274 opened Nov 11, 2024 by dame-cell
1
Resizing tokenizer leads to missing end token and garbage response?
#1273 opened Nov 10, 2024 by Mark-DelGrande
1
Jupyter notebook: No module named 'unsloth'
#1272 opened Nov 10, 2024 by iwouldratherbeatthebeach
3
feat: add option for using ADOPT optimizer based on Taniguchi, Shohei, et al. feature request Feature request pending on roadmap
#1270 opened Nov 9, 2024 by Selich
1
cannot load some models via vllm
#1268 opened Nov 8, 2024 by yananchen1989
11
save_pretrained_merged ruins my model
#1267 opened Nov 8, 2024 by Romiroz
1
Couldn't build proto file into descriptor pool! Invalid proto descriptor for file "sentencepiece_model.proto": sentencepiece_model.proto: A file with this name is already in the pool.
#1266 opened Nov 8, 2024 by CurtiusSimplus
9
LoRA on Qwen 2.5 does not patch qkv matrices
#1265 opened Nov 8, 2024 by MinghaoYan
1
triton.language' has no attribute cast [FIXED] fixed - pending confirmation Fixed, waiting for confirmation from poster
#1263 opened Nov 7, 2024 by arianyambao
11
train_on_responses_only doesn't work for Mistral models
#1262 opened Nov 7, 2024 by XiaomoWu
2
CAN'T LOAD: AttributeError: 'LlamaForCausalLM' object has no attribute 'update'
#1261 opened Nov 7, 2024 by yukiarimo
7
ValueError: Unsloth: Untrained tokens of [[128004]] found
#1258 opened Nov 7, 2024 by Hyfred
1
import unsloth causes error: pip install unsloth-zoo currently fixing Am fixing now!
#1252 opened Nov 6, 2024 by DaddyCodesAlot
5
AssertionError('initial value for logits error [FIXED] fixed - pending confirmation Fixed, waiting for confirmation from poster URGENT BUG Urgent bug
#1248 opened Nov 6, 2024 by daegonYu
10
ProTip! Mix and match filters to narrow down what you’re looking for.