forum

1495 threads · Page 16 of 30

Help! Cannot install! Pip install unsloth taking longer than usual 2 messages
Are Qwen 2.5 models supported for GRPO long context training? 4 messages
Issue with GGUF Conversion for Merged 4-bit Gemma 3 Model 163 messages
Open
Impossible to convert Gemma3 4b into gguf 13 messages
Open
How do you use your own datasets to train an ollama 3.2, 3B parameters using unsloth +google collab 6 messages
Expenses of training an 3.2 ollama model using unsloth and google collab 2 messages
Email filtering project: guidance 19 messages
Trying text classification with multiple classes 8 messages
GRPO training lead to empty responses 14 messages
How to integrate the checkpoint after finetuned the model finished into the base model using unsloth 7 messages
Open
Different results using different peft methods 11 messages
CalledProcessError 44 messages
High-Mem usage 7 messages
How can I run unsloth in rtx 5090? 2 messages
Training error 22 messages
Error loading model on Colab A100 4 messages
Guided Notebook for full_finetuning 13 messages
Is it possible to use "save_pretrained_merged" on offline environment? 17 messages
How to Fine-tuning llama 3.2 for long duccument summarization 24 messages
Loading My Own Model for Fine Tuning 51 messages
Lama 4 Scout Quantized Help 13 messages
loading Gemma3 lora finetunes via vLLM fails 11 messages
How can i see the fitting status 4 messages
Open
Facing error while pushing fine-tuned model to HF hub 6 messages
Code vulnerability analysis with Unsloth? 6 messages
Open
Need help with Tool/Function Calling 🥺 10 messages
Open
Gemma3_(4B).ipynb double <bos> token. 5 messages
Open
How to finetune a transformer so you add knowledge, without overfitting... 5 messages
Open
Unable to fine-tune gemma3-27b with 24gb vram 25 messages
VAPO support - training 5 messages
Finetuned Llama-3.2-11B-Vision to Ollama 14 messages
Parallel Tool Calls 2 messages
Which models use which templates? Are they interchangable? 4 messages
Unsloth pro 5 messages
Gemma 3 tutorial fails when switching from 4b to 1b 10 messages
Is there any multi-turn chat fine-tuning on webpage below 3 messages
is unsloth supported on sagemaker notebook? 2 messages
unsloth/gemma-3-4b-it error 8 messages
multi gpu availability for research use? 19 messages
Deploy Llama-4-Scout-17B-16E-Instruct INT4 / FP8 by VLLM 2 messages
Hi, could someone please help me? 22 messages
Unable to do GRPO with vllm & Lora, 3 messages
Solved
Input prompt (383 tokens) is too long and exceeds limit of 256 2 messages
Redownloads Model Every Time I run the This file? 4 messages
Always get the same error even though using default notebook: 3 messages
how to use deepseek v3 on python 5 messages
Running into issues saving using the training notebook. 40 messages
Open
How to calculate VRAM requirements for unsloth 7 messages
Solved
High Mem loading of 4bit gemma 3 3 messages
Open
Gemma 3 12b GRPO no improvement after 400+ steps - wrong hyperparameters? 6 messages