forum
Help! Cannot install! Pip install unsloth taking longer than usual
Are Qwen 2.5 models supported for GRPO long context training?
Issue with GGUF Conversion for Merged 4-bit Gemma 3 Model
Open
Impossible to convert Gemma3 4b into gguf
Open
How do you use your own datasets to train an ollama 3.2, 3B parameters using unsloth +google collab
Expenses of training an 3.2 ollama model using unsloth and google collab
Email filtering project: guidance
Trying text classification with multiple classes
GRPO training lead to empty responses
How to integrate the checkpoint after finetuned the model finished into the base model using unsloth
Open
Different results using different peft methods
CalledProcessError
High-Mem usage
How can I run unsloth in rtx 5090?
Training error
Error loading model on Colab A100
Guided Notebook for full_finetuning
Is it possible to use "save_pretrained_merged" on offline environment?
How to Fine-tuning llama 3.2 for long duccument summarization
Loading My Own Model for Fine Tuning
Lama 4 Scout Quantized Help
loading Gemma3 lora finetunes via vLLM fails
How can i see the fitting status
Open
Facing error while pushing fine-tuned model to HF hub
Code vulnerability analysis with Unsloth?
Open
Need help with Tool/Function Calling 🥺
Open
Gemma3_(4B).ipynb double <bos> token.
Open
How to finetune a transformer so you add knowledge, without overfitting...
Open
Unable to fine-tune gemma3-27b with 24gb vram
VAPO support - training
Finetuned Llama-3.2-11B-Vision to Ollama
Parallel Tool Calls
Which models use which templates? Are they interchangable?
Unsloth pro
Gemma 3 tutorial fails when switching from 4b to 1b
Is there any multi-turn chat fine-tuning on webpage below
is unsloth supported on sagemaker notebook?
unsloth/gemma-3-4b-it error
multi gpu availability for research use?
Deploy Llama-4-Scout-17B-16E-Instruct INT4 / FP8 by VLLM
Hi, could someone please help me?
Unable to do GRPO with vllm & Lora,
Solved
Input prompt (383 tokens) is too long and exceeds limit of 256
Redownloads Model Every Time I run the This file?
Always get the same error even though using default notebook:
how to use deepseek v3 on python
Running into issues saving using the training notebook.
Open
How to calculate VRAM requirements for unsloth
Solved
High Mem loading of 4bit gemma 3
Open
Gemma 3 12b GRPO no improvement after 400+ steps - wrong hyperparameters?