forum

1495 threads · Page 8 of 30

Fine-tuning Qwen 2.5-VL with multiple images in the prompt 2 messages
How to use unsloth/Qwen3-VL-8B-Instruct-unsloth-bnb-4bit in vLLM 2 messages
Multi-GPU support recognizing two GPUs (2x A4000 16gb) but says out of memory at 16gb (i have 32gb) 23 messages
Gemma-3n-E4B is not suitable for running with Colab Free? 3 messages
Training to reasoning as Legal 2 messages
Quesstion about CPT 11 messages
Error: supplied file was not in GGUF format 4 messages
GRPO + vllm on Google colab appears broken 35 messages
RuntimeError: One of the subprocesses has abruptly died during map operation.To debug the error,... 2 messages
Solved
LFM2 notebook is broken 3 messages
Open
Formatting training data for Bounding box detection using Qwen3-vl 12 messages
saving unsloth 4bit merged models not effective 2 messages
Open
Computing WER in eval with Gemma3 55 messages
Open
Unsloth GRPO Qwen 3 (4B) Colab Notebook Dependency Error 2 messages
SFTTrainer Issue | Qwen3_(4B) 12 messages
Open
SFTTrainer.train() Doesn't work 39 messages
What's the "Go-To" Method for Sharing a Model with a Custom-Trained lm_head? 20 messages
Solved
llama: Fast inference does not yet work with RoPE scaling - workarounds? 7 messages
Open
Long context OOM 3 messages
save_pretrained_gguf loops forever 39 messages
Open
Long context VRAM requirements 8 messages
Solved
[Bug] Runing the Inference on Spark TTS Model 9 messages
load adapters fail 12 messages
Open
DPO for Qwen VL 4 messages
Question about Continued Pre-trained (CPT) 3 messages
How to avoid messing up the base model when fine tuning? 2 messages
Unsloth model import into ollama 13 messages
Error while saving the gguf file 10 messages
Dataset Preparation for GPT-OSS-20B 39 messages
Open
GRPO gpt-oss-20b with 6k context length out of memory with 96 GB VRAM? 22 messages
Open
Is it possible to multi thread a fine tuned unsloth model(Qwen3-1.7B) 13 messages
Magistral Small 2509: Thinking not enabled in Ollama 2 messages
Open
GGUF File Creation Issue - Vision Support Missing After Conversion 13 messages
Unsloth: No config file found (gpt-oss finetuning) 3 messages
Finetuning in Legacy GPU and CUDA? 9 messages
Open
HELP! trainer.train() stuck in pytorch inductor compilation after 100-724 steps 16 messages
Model uploaded to HF has wrong embedding weight size 37 messages
Open
Qwen2.5-vl classification 5 messages
Save Vision Models in GGUF - Help me :) 23 messages
Open
Python GPT-OSS attention implementation 18 messages
Open
Gemma3N_(4B)-Audio.ipynb trainer error 6 messages
CUDA error: an illegal memory access was encountered 8 messages
gpt-oss save problem 3 messages
Solved
Newbie need help with AI Stuff any help is welcome 3 messages
Open
FastLanguageModel tokenizer encoding 7 messages
gpt-oss 11 messages
(official?) Colab notebook for Llama 3.2 finetuning not working - "Can not map tensor" 20 messages
Solved
ModuleNotFoundError: No module named 'unsloth' 24 messages
ImportError: cannot import name 'VLLM_SUPPORTED_VLM' 4 messages
Index Error during eval with GRPO Trainer 10 messages