Pinned issues
Issues
- 2
LLaMA-3.1-8B finetune: Unsloth does NOT load pre-finetuned QLoRA adapter correctly but its default ?
#1045 opened by thusinh1969 - 0
Qwen-2.5 Coder-7B-Instruct: ValueError: Unsloth: Untrained tokens found, but embed_tokens & lm_head not trainable, causing NaNs. Restart then add `embed_tokens` & `lm_head` to `FastLanguageModel.get_peft_model(target_modules = [..., "embed_tokens", "lm_head",])
#1053 opened by dante3112 - 0
A package issue?
#1052 opened by savour-it-last - 0
about finetuning
#1051 opened by djahzo - 0
- 0
- 2
qwen2.5 support?
#1043 opened by milsun - 0
- 2
Fine tune and infer llama3 with cpu
#1037 opened by SidneyLann - 0
RuntimeError: Unsloth currently does not support multi GPU setups - but we are working on it!
#1046 opened by YasamanJafari - 5
Llama 3.1 (8B) fine-tuning demo suddenly stopped working during local training.
#1010 opened by brainchen2020 - 1
- 1
- 1
ValueError: Unknown RoPE scaling type longrope
#1042 opened by XCYXHL - 4
What is the right way to load Qwen2's chat interface?
#1040 opened by brando90 - 1
Issue With Mistral Small
#1044 opened by DaddyCodesAlot - 3
- 2
- 6
Can we continue finetuning LlaMA-3.1-8B's QLora pre-finetuned adapter with Unsloth to extend context length ?
#1032 opened by thusinh1969 - 6
Any Plans To Support Solar Pro?
#1031 opened by DaddyCodesAlot - 3
Internlm2_5 support
#1007 opened by Ammar-Alnagar - 4
- 3
Feature Request: Qwen2-VL support
#1020 opened by 0xSt1ng3R - 5
release cycle
#1002 opened by aarnphm - 5
ModuleNotFoundError: No module named 'unsloth'
#1030 opened by vidithirve - 3
More problems with train_on_responses_only
#1017 opened by LostRuins - 2
- 2
When Flash Attention 2 is used and "use_dora = True", errored out: "RuntimeError: FlashAttention only support fp16 and bf16 data type"
#1013 opened by rohhro - 2
Flash Attention 2 doesn't work with Gemma 2 models
#1014 opened by rohhro - 4
Unsloth & XFormers keep crashing on each other !
#1026 opened by thusinh1969 - 4
- 2
Train on responses only does not work with TinyLlama-chat
#1015 opened by akhlakm - 1
Should throw exception for the current text generation call will exceed the model's predefined maximum length (8192)
#1016 opened by SidneyLann - 14
- 1
Full Finetune with Unsloth
#1021 opened by user074 - 2
RuntimeError: Failed to import transformers.data.data_collator because of the following error (look up to see its traceback): maximum recursion depth exceeded
#1022 opened by karacupa21 - 2
Add support for Qwen2Audio
#1018 opened by jonflynng - 1
target_modules "embed_tokens", "lm_head" really needed? try out FT with Nous Research LLAMA31 8B
#1024 opened by carstendraschner - 5
- 2
model.push_to_hub_merged saves padding_side = "left"?
#1006 opened by Karoljv - 2
Issues with saving to hub -> Gemma based models
#1005 opened by Ammar-Alnagar - 2
Problem with Phi 3.5
#1003 opened by DRXD1000 - 2
RuntimeError: expected self and mask to be on the same device, but got mask on cuda:7 and self on cuda:0
#996 opened by Silentssss - 2
Installation on Kaggle no longer works
#998 opened by abedkhooli - 1
push_to_hub_merged: How can I push to an organization?
#1009 opened by ysy970923 - 1
- 2
Can this fine tune the llama3.1 70b model
#995 opened by xwan07017 - 0
Loading from Checkpoint
#997 opened by MuhammadBilalKhan267 - 1
`construct_chat_template` raises RunTimeError for default template with trailing newline
#992 opened by rodrigomeireles - 1
"multiplicative LoRAs" for LLMs?
#991 opened by jukofyork