forum
Fine-tuning Qwen 2.5-VL with multiple images in the prompt
How to use unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit in vLLM
Multi-GPU support recognizing two GPUs (2x A4000 16gb) but says out of memory at 16gb (i have 32gb)
Gemma-3n-E4B is not suitable for running with Colab Free?
Training to reasoning as Legal
Quesstion about CPT
Error: supplied file was not in GGUF format
GRPO + vllm on Google colab appears broken
RuntimeError: One of the subprocesses has abruptly died during map operation.To debug the error,...
Solved
LFM2 notebook is broken
Open
Formatting training data for Bounding box detection using Qwen3-vl
saving unsloth 4bit merged models not effective
Open
Computing WER in eval with Gemma3
Open
Unsloth GRPO Qwen 3 (4B) Colab Notebook Dependency Error
SFTTrainer Issue | Qwen3_(4B)
Open
SFTTrainer.train() Doesn't work
What's the "Go-To" Method for Sharing a Model with a Custom-Trained lm_head?
Solved
llama: Fast inference does not yet work with RoPE scaling - workarounds?
Open
Long context OOM
save_pretrained_gguf loops forever
Open
Long context VRAM requirements
Solved
[Bug] Runing the Inference on Spark TTS Model
load adapters fail
Open
DPO for Qwen VL
Question about Continued Pre-trained (CPT)
How to avoid messing up the base model when fine tuning?
Unsloth model import into ollama
Error while saving the gguf file
Dataset Preparation for GPT-OSS-20B
Open
GRPO gpt-oss-20b with 6k context length out of memory with 96 GB VRAM?
Open
Is it possible to multi thread a fine tuned unsloth model(Qwen3-1.7B)
Magistral Small 2509: Thinking not enabled in Ollama
Open
GGUF File Creation Issue - Vision Support Missing After Conversion
Unsloth: No config file found (gpt-oss finetuning)
Finetuning in Legacy GPU and CUDA?
Open
HELP! trainer.train() stuck in pytorch inductor compilation after 100-724 steps
Model uploaded to HF has wrong embedding weight size
Open
Qwen2.5-vl classification
Save Vision Models in GGUF - Help me :)
Open
Python GPT-OSS attention implementation
Open
Gemma3N_(4B)-Audio.ipynb trainer error
CUDA error: an illegal memory access was encountered
gpt-oss save problem
Solved
Newbie need help with AI Stuff any help is welcome
Open
FastLanguageModel tokenizer encoding
gpt-oss
(official?) Colab notebook for Llama 3.2 finetuning not working - "Can not map tensor"
Solved
ModuleNotFoundError: No module named 'unsloth'
ImportError: cannot import name 'VLLM_SUPPORTED_VLM'
Index Error during eval with GRPO Trainer