forum

1495 threads · Page 6 of 30

Is it possible to fine tune glm-4.5V for vision? 3 messages
Training Qwen3 8B 19 messages
QAT fine-tuning 10 messages
error in code 34 messages
Gemma3-12B-finetuning 2 messages
Bootstrap Relative Policy Optimization 3 messages
Open
Does Unsloth w/ ART work with GPT-OSS:20b? 7 messages
What changes are to be made to switch to Dr. GRPO from an existing GRPO file? 5 messages
Solved
Help Training version of models and merging 8 messages
Open
Gemma3-27B-finetuning (image and text) 4 messages
ValueError: Invalid input type. Must be a single image, a list of images, or a list of batches of im 9 messages
Open
Qwen fails to extract Names along with their bounding boxes from images 3 messages
failing to save model after training 24 messages
Want to help work on support for diffusion models for college project. 16 messages
Prefered image resolution for qwen3 vl 8b 127 messages
Qwen 3 32B Base 3 messages
GRPO OOM Error partway through training 8 messages
Solved
auto find batch size 4 messages
help with changing so i get accuracy while training 24 messages
accuracy while training 2 messages
Poor quality at inference using Ollama or llama.cpp 2 messages
Llama3.1 fine tuned model finetuning 6 messages
Export to Ollama on VM 2 messages
Summarization task 15 messages
official ollama models vs unsloth GGUF 3 messages
Open
About finetune with video on Qwen3-VL with unsloth 21 messages
Open
gemma 3n failed training 27 messages
How do I mask data properly 5 messages
Fine tuning on non-reasoning data but inference with reasoning on 3 messages
Vision Fine Tune with mixed dataset 5 messages
Open
data preparation for instruct sft 25 messages
Fine-Tune Whisper_large_v3_turbo.SST 16 messages
Open
train model. 2 messages
How do I create a custom datasset that can be used with Unsloth? 12 messages
Multi-GPU Support for GRPO Training with Vision-Language Models 4 messages
Open
GPT-OSS 20B - train_on_responses_only 4 messages
Open
Qwen3 - Train on Responses Only 3 messages
Query About Flash Attention 2 messages
How to downgrade Unsloth 12 messages
Open math reasoning by unsloth 2 messages
Are you looking for developer? 2 messages
i cant run torch (& gpu) on jupyter notebook for unsloth 11 messages
DDP with Unsloth 7 messages
Qwen3-VL 8B Instruct — Text Training Workflow for Domain Adaptation using Unsloth 30 messages
UserWarning: Model qwen3-32b-bnb-4bit not found locally or on HuggingFace 32 messages
Can't figure out why my finetuned model never gets better than base... 2 messages
Revision argument in push_to_hub_merged not being used 8 messages
4-bit Quantization after save_pretrained_merge for Qwen3-VL-8B 3 messages
Error when attempting to load Granite 4.0 - h 350M model 3 messages
trying to finetune on a quite complex dataset including alot of images of text 81 messages