forum
Being forced to log into wandb.ai?
Solved
Issues while merging base model(llama3.2) with adapter(lora)
What does it mean when a model seems like it doesnt know anything about your dataset?
Open
ValueError: numpy.dtype size changed, may indicate binary incompatibility. Expected 96 from C header
Solved
Fill in the middle fine tuning
Solved
Is learned prompt tuning available in Unsloth?
Multi-Turn GRPO Brainstorming: Non-deterministic tool feedback
Fine tuning Llama-3-8B-Lexi-Uncensored on custom dataset - LR not declining
Fine Tuning for Regression
Gemma 3 notebook: saving GGUF broken
Open
RuntimeError: CUDA device-side assert triggered (Unsloth GRPO, Multi-GPU, Qwen 2.5 14B Training)
Open
How do I get a ref to a model/lora I created?
4 bit load error
Failed to install Triton.
Solved
Questions regarding submission for hiring challenge
Open
Finetuning unsloth/Pixtral-12B-2409 vision dataset error
How to know if QLoRA or LoRA is being applied
Question about how performance is evaluated for puzzle A
Multiple data type mismatches when finetuning Llama 3.2 Vision locally
Open
Qwen-2.5-Coder-32B-Instruct fine-tuning training loss drops too fast
Open
Training stops after first step
Really quick question about problem B in unsloth challenges
Qwen2.5-VL 7B Full Fine-tuning | CUDA out of memory | Colab Only
Doing a QloRa cold start fine tuning before GRPO
Clarification about Problem E in the Unsloth Puzzles
Unsloth: Failed to create dynamic compiled modules!
Open
RecursionError: maximum recursion depth exceeded
Finetuning doesn't learn the LLM anything.
Failed to create dynamic compiled after March updates
Solved
Merging resets model performance LORA
name error:name 'bias' is not defined
NameError: name 'bias' is not defined
Why the instruction is not masked with -100 in label during instruction fine tuning.
Open
RuntimeError: Failed to find C compiler. Please specify via CC environment variable.
Open
Kaggle for fine tuning Llama3.1_(8B)-GRPO.ipynb (I'm using the starter code) error when using peft
Open
Unsloth example fintuning Colab failing when creating SFTTrainer
CUDA out of memory for Custom Dataset [Qwen2-VL-7B-Instruct]
Solved
finetune r1 distill model question
Open
Attribute Error with SFTTrainer
Out of Memory during GRPO training
Practical Reinforcement Learning Examples Showcasing Unsloth's potential
Open
fine tuning Llama-3.2-11B-Vision-Instruct with no success
Qwen-2.5 GRPO finetune without vLLM
vllm inference of lora finetuned unsloth model
Code formatting of PRs for the `zoo` repository
Issue with save_pretrained_merged
Open
Load LORA Adapters and use for inference
i want to fine tune the vision model.How can i prepare my owndataset
OpenAI Compatible Server w/ DeepSeek-R1-dynamic-1.58-bit model
Cannot Merge 4bit after GRPO
Open