forum

1495 threads · Page 14 of 30

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cuda:1) 6 messages
Reproduction with unsloth 2024.12.4 12 messages
Open
Training Model with Markdown Files 6 messages
train model with personal data 4 messages
Open
Turn off reasoning for Qwen models 4 messages
Solved
TOOL IN GEMMA-3 2 messages
Gemma3-Fine-tuning with dataset 119 messages
Fine tuning llama 3 model 5 messages
Open
What is the most realistic Open TTS currently? 7 messages
Open
Unsloth GRPO trainer is corrupting my model 211 messages
Solved
how can i set the max new tokens to not affect the think text? // make generation faster 15 messages
Qwen 235b repeating itself endlessly 5 messages
Multi-GPU - accelerate launch - Expected to mark a variable ready only once 6 messages
RuntimeError: PassManager::run failed While fine-tuning qwen2.5-7b-it model 3 messages
qwen3 architecture 6 messages
TTS Model Performance 2 messages
Open
Unsloth BLIP2 Finetuning 78 messages
Advice on GRPOing a brainrot thinking model 3 messages
Unsloth tutorial for HF LLM 6 messages
How can one set Output Data Type as Float? 2 messages
Open
Unsloth: Saving LoRA finetune failed 19 messages
Gemma3 27b it - outputs repeating text for long answers when using the original safetensor version 3 messages
Open
Does the number of CPU Threads affect "train" or "train_on_responses_only" in Unsloth? 4 messages
Open
OSError: <model> does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model 23 messages
Open
Support for NVIDIA 5000 Series GPU 4 messages
Open
Phi_4-Conversational - train loss explode during first epoch 11 messages
Error while importing unsloth (linux) 24 messages
Solved
AttributeError: 'int' object has no attribute 'mask_token' 80 messages
dataloader_drop_last give same result without using it 37 messages
Error in Inference on model HuggingFaceTB/SmolVLM-Instruct 2 messages
Error in Qwen 3 4b GRPO Tutorial Notebook 14 messages
Inferencing Gibberish text even after tuning T, Min_p 12 messages
Solved
Help with Synthetic Data Kit 36 messages
Error with finetuning CSM 1b 20 messages
Open
RuntimeError: Direct module loading failed for unsloth_compiled_module_siglip: Unexpected optimizati 3 messages
Open
compute_metrics not working as expected 8 messages
Need multigpu support for an opensource project 13 messages
Help with SFT Qwen3 model 12 messages
Support for fine-tuning multimodel models with Qwen 2.5 7B,the inference result is no correct. 11 messages
help 17 messages
installing unsloth on M1 mac laptop 10 messages
Finetuning Deepseek-r1 on reasoning trace 3 messages
Solved
Dependency Issues on Runpod 13 messages
how hard would it be to add mono intern training support to unsloth? 3 messages
Support for fine-tuning multimodal models with GRPO 2 messages
Open
GGUF HF update cadence, road map, or announcements 5 messages
Solved
Qwen3 model outputs seem broken 32 messages
Noob needs some support with fine-tuning 3 messages
[Bug] Still not able to export Gemma3 to gguf. My boss is pressing me 18 messages
Solved
Spark_TTS_(0_5B).ipynb 'Qwen2Model' object has no attribute 'model' 5 messages
Solved