forum

1495 threads · Page 13 of 30

Batch inference broken with Gemma2 16 messages
Mistral 3.2 Finetuning with Unsloth + Serving with vLLM 4 messages
Open
Cannot Fine-Tune Gemma-3N with Images 94 messages
Is the dots LLM supported? 7 messages
Slow Inference with fine-tuned Qwen3 11 messages
Solved
Devstral-Small-2507-GGUF:IQ2_XXS does not support tools 3 messages
Data Format (JSON Input) 5 messages
Multi-GPU in Unsloth. 9 messages
Qwen3 notebooks use SFTTrainer instead of Unsloth Trainer any reason ?? 4 messages
Open
Finetuning SparkTTS0.5B not working 4 messages
Open
TypeError: unsupported operand type(s) for +: 'Tensor' and 'NoneType' 7 messages
Gemma 3 Fine Tuning - Tons of vram needed? 8 messages
Zero Divison error during training 3 messages
Gemma 3n Colab Notebook Not Working 128 messages
Modelfile missing 4 messages
Open
Can I use bone stock Qwen3 1.5B Instruct model for finetuning? 4 messages
Test question 4 messages
Worse performance while jailbreaking Llama 2 messages
Having an issue with VLM qwen2.5 VL inference 4 messages
i am having this error while i am trying to fine tune gemma 3 3 messages
Open
GRPO training CUDA memory issue 3 messages
Fine Tuning Qwen 3 2 messages
Issue with Synthetic-data-kit + Unsloth + vLLM 4 messages
MI300X Training Speeds 5 messages
SparkTTS Colab breaks on inference 10 messages
qwen 2.5 vl error 2 messages
Negative loss during training 18 messages
Open
Multimodal finetuning of Gemma3N 12 messages
qwen3-30b-a3b finetuning 12 messages
I need a skilled AI/ML consultant who has native level of English 3 messages
llama.cpp error: 'invalid unordered_map<K, T> key 5 messages
Open
Qwen 2.5vl RuntimeError 5 messages
how to specify max_seq_length when using unsloth train_on_responses_only? 23 messages
Docs website error 2 messages
Qwen 2.5 Vl 7B Instruct 2 messages
How to include Validation Loss? 2 messages
RuntimeError: Direct module loading failed for unsloth_compiled_module_phi3: positional argument fol 2 messages
Solved
Gemma3 quantization below Q8 3 messages
Open
No longer "smartly offloading gradients to save VRAM"? 6 messages
Open Solved
[Gemma3] Please help with correct dataset formatting 38 messages
AttributeError: 'LlamaForCausalLM' object has no attribute 'load_lora' 8 messages
GRPO run with Qwen3-4B 8 messages
❌ GGUF conversion failed - n_tensors = 0 during save_pretrained_gguf 2 messages
Open
Been trying to try out the GRPO Notebook 14 messages
Problem with long context finetuning 5 messages
A dependency updated and I can't seem to get Unsloth to run anymore. What am I doing wrong? 4 messages
Model Architecture Suggestions for Grammar-based Models 25 messages
SFT -- error logging eval_loss 6 messages
Nanonets OCR model quantizeed with unsloth in ollama 7 messages
Open
Runpod template 3 messages
Open