forum
Offline resources
Cannot run trainer.train() — backward-graph RuntimeError
[Support Request] Need Working Code for Original Qwen/Qwen2.5-VL-7B-Instruct Model Fine-tuning
Not able to run unsloth gemma 3 bnb on with dynamic lora on vllm?
Open
GRPOTrainer compute_loss function shape mismatch for matmul
multi gpu
GRPO Standby H100
help with test train split
Gemma 3n Training Notebook Fail
Solved
ValueError: Supplied state dict for model.layers.0.mlp.experts.down_projs.0.weight does not contain
finetuning SmolLM-135 for coding generation
Open
Unsloth with 9070 XT in Fedora 42 (ROCm 6.3.1.1)
Support for Gemma 3N model vLLM support
FINETUNE unsloth/gemma-3-4b-it but result really badddddd
Open
Unsupported: Unsupported Tensor.requires_grad_() call
Cannot finetune Qwen3Next 4bit BnB -- Compatibility issues
Open
regarding your new
How to merge multiple LoRA adapters (vision + text) for combined inference in Unsloth?
load_in_8bit and KeyError: ""
Finetuning Gemma 3 4B/12B/27B on multi-image datasets
cuda version
How to calculate F1 Score and Accuracy when training with Unsloth?
Open
VLLM OOMs on small models.
Open
gpt oss 20b and KeyError: ''
Does Dora work with Unsloth?
Gemma-3 1B - Saving a GGUF results in a bad model
code says to try increasing max_seq_length but that fixes nothing
Fine-tuned unsloth/gemma-3-1b-pt model produces gibberish/empty output after quantization (GPTQ/AWQ/
unable to push to hf
Difference between training with 'load_in_4bit' vs a pre quantized bnb-4bit model
What sampling settings does unsloth use during training
Open
error when finetune Qwen2.5-vl-7b, but it's fine in gemma-3-4b-it and gemma-3-12b-it
RuntimeError: Boolean value of Tensor with more than one value is ambiguous
Solved
AttributeError: module 'transformers.models.bit.modeling_bit' has no attribute 'Linear'
'Qwen2Config' object has no attribute 'text_config'
unsloth trainer code work 13 days ago, now same code give runtime error: boolean value of tensor...
Bots only?
Sequence classification notebook no longer works:
Does Unsloth have quantized versions of optimizers other than AdamW?
Open
there is an error when finetuning gemma-3-12b-it by lora
Just chat with bot
Gemma support
Help needed: Converting fine-tuned llama3.2-vision model to GGUF format
gpt-oss: can't load local checkpoint
Saving GPT-OSS as .GGUF
Help Needed: Running Llama3.2 (11B) Vision Notebook on A100 Runtime
Issue with LoRA Merge Inference on L4 Machine Using Unsoth
Temporary - just to use the bot
Open
[Bug] Garbled text output likes ה during inference when UNSLOTH_VLLM_STANDBY=1 is enabled using Qwen
Is it possible to update a GRPO notebook to use LLM feedback?