forum
Is the dataset passed to `UnslothTrainer` shuffled by default?
Open
GRPO fails in terms of accuracy in datasets different than gsm8k
Any plans for Unsloth Dynamic 2.0 GGUFs for DeepSeek V4 Flash?
Open
Unusual loss curves
Env mask for custom rollout_func
Solved
Speech to text models training without other language performance degradation
how to install unsloth in offline environment
trying to find something that can create a bot for tetris
Alternatives to qlora finetuning on qwen3.6 27B with rtx5090?
No cuda support on last update unsloth 2026.5.2 is up to date
Open
Unsloth loading model weights at full precision even though I have manually set it to load at 4 bit.
Solved
Trying to find simple GPRO/RLHF example (no reasoning)
Open
Qwen 3.6-27B only text-to-text in llama.cpp
Qwen3.5-122B-A10B-GGUF Reasoning/Tool call issues
Windows AMD ROCm issue
Bug in Unsloth Docker Upload Failed
Open
UnslothGRPOTrainer switches on gradient checkpointing when it shouldnt
Strix Halo Unsloth fails to detect unified memory (0.35GB VRAM)
Open
Speculative decoding: `--spec-ngram-size-n` argument has been removed
LoRA for TokenClassification
Unsloth Studio + remote Training
Open
Unsloth Studio + vLLM
Open
Help me to build a RIG
Open
Silent hang on Vision DPO path with Gemma 4 E4B
Solved
weird mismatch error in grpo multi image training
How do I work around OOM on LoRA merge?
Solved
Merging lora weights from checkpoint into base model
Why does unsloth-zoo depend on torch < 2.11.0?
Open
Where are settings for splitting models across multiple gpus/CPU ram + Vram?
Agents Support not working in Unsloth Studio
Open
self and mat2 must have the same dtype, but got Half and BFloat16 - GRPO Lora Training
Solved
torch._dynamo.exc.Unsupported: HigherOrderOperator
Solved
Installation Error [Windows]
Solved
How to load custom dataset into Unsloth Studio
Solved
Linux install Unsloth Problem
Qwen Coder with Unsloth Studio API Error 405
Open
Confirm that native long context extension built into Unsloth
Open
Opinion: I want to fine-tune a model for PII/PHI detection. Qwen3.5 2B (via unsloth) vs BERT-based?
Open
Does Unsloth really support video finetune?
i want to use the unsloth studio in kaggle, how can i do that?
Open
Path Handling in Windows
Unable to run Unsloth's DeepSeek OCR on Google Colab
qwen 3.6 mlx quants dont support reasoning on lmstudio
Trying to run unsloth/gemma-4-E4B-it-GGUF, quant: UD-Q4_K_XL
Colab Qwen3 phone deployment
Open
Solved
Error Importing Unsloth
Latest Ernie text to image model GGUF inside unsloth studio
Open
colab - Unsloth studio
Open
Fine-tuning multiple datasets of different domains and different size (no of rows)
Gemma e4b error on Colab[A100] FlashAttention forward only supports head dimension at most 256