forum

1495 threads · Page 21 of 30

Saving LoRa weights only 17 messages
Stable diffusion Model 17 messages
Open
when I do unsloth_train(trainer) why is this only showing Training loss not other metrics? 6 messages
Open
I want to use DPO on vision language models like Pixtral, any 3 messages
How to import and deploy a pre-trained texttoimage model on Google Cloud for a high-traffic project? 14 messages
Open
Phi4 FineTune Colab. Training arguments being ignored? 3 messages
CUDA out of memory 10 messages
Open
Is it possible to fine tune Llama-3.2-11B-Vision-Instruct without image input? 4 messages
Open
Phi-4 endless generation 14 messages
error when training granite-3.1-2b 28 messages
Error trying to use Unsloth on local Jupyter notebook: NameError: name 'MistralConfig' is not define 10 messages
train_on_responses_only with Gemma 2 7 messages
I want to continue pre-training a large language model with custom data 5 messages
fine tuned model not listed in unsloth or not supported (not unsloth\XXXX) 3 messages
Fine-tuning vision model 9 messages
What's the most painful when working on LLM projects? 2 messages
Training vision in 4bit and saving to 16bit 54 messages
Solved
Confusion in applying chat template 7 messages
Where are models saved? 11 messages
Open
Longer context training for llm models 16 messages
Getting error running inference on cpu 12 messages
What about parameters like min_p repeat_penalty top_p top_k during fine-tuning? 2 messages
Custom Tokenizer makes Qwen2-VL-2B model keeps generating text even after reaching the '<|im_end|>'. 3 messages
Open
NONE OF VISION MODELS ARE WORKING FOR FINE-TUNES 19 messages
Open
im new to unsloth and fine tuning, watched a bunch of videos can you share the best videos uve found 4 messages
Ethical filters in trained models 19 messages
Finetuning done, Exported to OLLAMA as instructed as well, but cannot run it locally with OLLAMA 6 messages
Seek Help with Unsloth's output GGUF and import issues to platform like Ollama 4 messages
Open
Error when finetuning Cohere based Models 4 messages
Solved
OpenAI format JSONL dataset 321 messages
Open
Vram requirments in a list? 4 messages
Gemma 2 <bos> token 2 messages
Finetune an existing finetune (NuExtract) 23 messages
Open
Continued Pretraining 5 messages
I have been trying to create a docker image where flash-attn works 3 messages
Optimizing Llama 3 Training on H100: How to Balance Batch Size and GPU Memory Utilization 8 messages
Does Unsloth support benchmark evaluation callbacks? 4 messages
Open
What is the best way to deploy finetuned llama 3.2 11B? 11 messages
fp16 fp32 error 15 messages
NameError: name 'dataset' is not defined 17 messages
Open
Issues pushing vision models to hub using unsloth 3 messages
Open
‼AttributeError: 'NoneType' object has no attribute 'attn_bias' 8 messages
Building an advanced conversational AI with web/api access 7 messages
Google Cloud build/run 2 messages
Restarting Training from Lora Saved Model 6 messages
Open
Noob SFT Advice (Qwen) 5 messages
Open
huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' 4 messages
Open
Help for dataset generation 3 messages
Open
Train a model from scratch 3 messages
AttributeError: 'LlamaAttention' object has no attribute 'rotary_emb 23 messages