forum

1495 threads · Page 11 of 30

Trying to backward through the graph a second time (or directly access saved tensors after they have 5 messages
Test 3 messages
Classification weights not loading 7 messages
Open
Proper Support for RTX 5070 (5000 Series GPUs) - Unsloth 55 messages
Avoiding overfitting 4 messages
Unsloth issues with Medgemma 27B model (unsloth/medgemma-27b-text-it-bnb-4bit) 35 messages
GRPO: No attribute "disable_adapter" 123 messages
Open
Repeat all instructions 6 messages
Dynamic 2.0 GGUF Quants 2 messages
Open
Difference between google/gemma-3n-E4B-it and unsloth/gemma-3n-E4B-it 9 messages
Fine Tuning Embedding with Unsloth 2 messages
Open
Gpt-oss -20b- f16 24 messages
DeepSeek V3.1 Help - any quant guide I can read 5 messages
Open
The batch_size will be automatically reduced, and the training will restart from the first step. 3 messages
Gemma 3 4b training not starting, help! 11 messages
Open
Can I use Unsloth to fine-tune model for sequence classification? 5 messages
Error when finetune with Orpheus notebook 3 messages
Distilled-Deepseek R1 does not learn or even gets the scope of the wanted output. 2 messages
Blackwell 5090 and RTX Pro - Working Dockerfile 18 messages
Help regarding continious pretrain on gemma3 270M 19 messages
Guidance on Choosing the Best Model for My Project 6 messages
Open
Want to push the finetuned 4bit model to hugging face 2 messages
Open
got-oss-4bit 2 messages
ValueError: binary mode doesn't take an encoding argument 2 messages
Link missing for Hyper-parameter tutorial 6 messages
4-Bit Quant 11 messages
Gemma finetuning train_on_responses_only Error 11 messages
Crash on unsloth import in cluster environment (V100, no root) 4 messages
How to set good parameter when fine tuning? 12 messages
Open
Multi-GPU possible for SFT with Unsloth? 2 messages
Solved
Llama 3.1:8b notebook error 10 messages
Solved
gpt-oss-120b-F16 (gibberish answer) 11 messages
Open
gpt-oss LoRA running 12 messages
Constant OOM Problem 9 messages
Open
Unsloth currently only works on NVIDIA GPUs and Intel GPUs 22 messages
Open
UnSloth discord ai? 4 messages
Horiza 2 messages
Open
Hey I have a request 7 messages
Open
"RuntimeError: shape '[-1, 8]' is invalid for input of size 7" while training with GRPO 5 messages
Docker Desktop container for GPT‑OSS‑20B (F16) not utilizing my NVIDIA GPU 4 messages
Fine-tuning Llama 3.2 - OOM Crash During Eval 7 messages
Qwen3-4B-2507 talking crazy in Ollama 36 messages
Open
load_in_4bit 7 messages
How long will it take for GPT -oss 20b to come into 4-bit quantized 9 messages
How to further finetune a model from a checkpoint 2 messages
gpt-oss:20b not loading on Mac using transformers library from Huggingface 3 messages
OpenAI OSS - Not formatting outputs correctly 6 messages
Open
Noob looking to train an abliterated R1 model 12 messages
Slow training speed 4 messages
Open
save_pretrained_merged create a .cache folder 7 messages