forum

1495 threads · Page 25 of 30

General advice for instruction-tuning a base model 2 messages
Set a seed 3 messages
triton library not found! 4 messages
Mistral Nemo 12B 8-bits inference is not working 7 messages
Run Unsloth on a different GPU 3 messages
Notebook tutorial for multi-label classification 3 messages
Out of Memory on RTX 3060 Laptop GPU with 4-bit Quantization 3 messages
Solved
Bogus results after finetuning 13 messages
How can I access unsloth pro version? 3 messages
Google Colab to HuggingFace Error 3 messages
Open
Google Collab to Ollama gguf 6 messages
Model does not stop generating during inference after fine-tunning. 6 messages
ImportError on Paperspace: libcusparse.so.12: undefined symbol 25 messages
Solved
Model finetuned generate responses without stopping : llama3 5 messages
save adapter only vs save merged_16bit 23 messages
LoRA Adapter warnings in vllm 2 messages
🍲Agent Chef🥘: LORA MERGE ISSUE 95 messages
Fine tuning with text dataset! 5 messages
Deep speed support 18 messages
I have a 3080 with 12 GB of RAM, and I'm trying to fine-tune "unsloth/Phi-3.5-mini-instruct-bnb-4bit 19 messages
Open
Using the example chat template for OLlama raises RuntimeError 13 messages
Open
Unsloth models deployment documentation ?????? 12 messages
Open
Fine-tuning multiple times 4 messages
Just got No module name triton error 9 messages
Solved
GGUF Upload - Suuuper large file 5 messages
Change the code instruction template in unsloth to match the gemma 2 instruction template 22 messages
Open
Unsloth 4bit model - is it something different? 25 messages
Open
Has anyone else run into this error with the latest Unsloth, accelerate, and TRL regarding DPO? 5 messages
Erractic bug in Phi 3.5 Did you mean: 'short_cos_cached'? 4 messages
Bug in DPO Zephr Unsloth Example notebook 2 messages
whats up with the llama 3.1 tokenizer? 7 messages
Open
Quantization Issue 35 messages
Deployment of finetuned llam3 7B model on aws sagemaker jupiterlab notebooks ? 7 messages
Finetuning Llama Instruct model - DataCollatorForSeq2Seq error 2 messages
Finetune Nemo 12b with ShareGPT conversational style dataset 2 messages
cpu 3 messages
AttributeError: 'UnslothTrainingArguments' object has no attribute 'packing' 3 messages
LM studio does not recognize my model 2 messages
Solved
Does unsloth provide "train_on_inputs"= False parameter similar to axolotl? 2 messages
Open
how to connect trained model with unsloth to RAG and How to teach unsloth model to say"I don't know" 8 messages
I want to change the training from 4bit to 16bit 4 messages
continue fine tuning after outputting the adapter 2 messages
Production inference 4 messages
Chatml for Qwen Model 2 messages
Hi. Just tried to perform fine tuning on tinyllama but only the model unsloth/tinyllama-chat-bnb-4b 2 messages
Data Preparation Tutorial for Fine-Tuning a Model 2 messages
Unsloth with TRL DPO 7 messages
Solved
Issues with back propogatting a loss through a lora adapted unsloth/tinyllama-bnb-4bit model 3 messages
Data preparation for Chat. I only have long chunks of proprietary text data. 2 messages
Open Solved
Hosting model on Huggingface's Inference Endpoints? 13 messages
Open