forum

1495 threads · Page 24 of 30

#help DPO finetuning qwen models 7 messages
A possible way to automatically detect more modules to be optimized that make Finetune faster 3 messages
Open
Saving to gguf - Downgrade the protobuf package to 3.20.x or lower. 2 messages
does not appear to have a file named config.json 2 messages
Loss stuck on 0.6931 on DPO training 30 messages
support for encoder-only and encoder-decoder models 4 messages
Can't load tokenizer 5 messages
Custom Eval metric in training 14 messages
Open
Tokenizer load error 27 messages
HFValidationError 7 messages
Tips on improving quality of lower parameter model's generation 16 messages
Open
The attention mask is not set and cannot be inferred from input because pad token is same as eos tok 10 messages
UndefinedError: 'str object' has no attribute 'role' when mapping dataset. 7 messages
Open Solved
llama 3.1 orpo / dpo kaggle 4 messages
Origanl saved model doesn't work and gguf in ollama either 8 messages
Fastest way to do inference on trained model 19 messages
Open
The model did not return a loss from the inputs 3 messages
Solved
Using Unsloth + trl Online DPO 2 messages
Finetuning Llama 3.2 1B 3 messages
Open Solved
Phi 3 (unsloth/Phi-3-mini-4k-instruct) giving random responses 2 messages
Open
creating and using custom dataset 17 messages
Open
Does it make sense to load and finetune a model in q4 quantization and later on export it as 8 bit? 3 messages
Remove <|eot_id|> after fine-tuning Llama3.2-1B-Instruct 20 messages
Solved
Using Unsloth fine tuned model in transformers.js 5 messages
Gemma 2 issues on raw pretraining 11 messages
Open
Fine-Tuning Llama3.1 Issues 30 messages
Open
Zero train loss 6 messages
Open
Llama runner process has terminated: error loading model: error loading vocabulary 10 messages
Cannot adapt 4bit finetuning of llama 3.1 to 8bit, with lora. Help? 3 messages
How to get thousands of documents/books into prompt-completion pairs for instruction fine-tuning ? 17 messages
GGUF / llama.cpp Conversion Error 2 messages
Exception: data did not match any variant of untagged enum ModelWrapper at line 757452 column 3 3 messages
Qwen2.5 14B Instruct giving padding error 10 messages
Unrecognized processing class in unsloth/Llama-3.2-11B-Vision 4 messages
How I can use Speculative Decoding with Unsloth 4 messages
Unable to Run Models: Llama-3.2-3B and Llama-3.2-3B-Instruct 5 messages
Solved
KTO Without Reference Model 4 messages
Open
Finetuning on Llama 3.1 instruct version throws Untrained tokens found error 12 messages
Open
KTO Trainer not functioning. 4 messages
Issue when resuming from checkpoint 3 messages
Solved
Im new with AI and Unsloth, I have some question. 8 messages
Open
Alpaca Chat Template Issue with vLLM API 2 messages
finetune Qwen2.5 coder instruct 4 messages
Llama 8B model for inference giving drastic results when loaded from locally saved model. 3 messages
Issue loading model: unsloth/Meta-Llama-3.1-8B-bnb-4bit does not appear to have a file named config. 3 messages
Continuous pre-training on instruct model? 86 messages
How to convert unsloth model to standard HF model e.g., to lead to vLLM? 3 messages
0.5B model usage is more than 100G GPU RAM?! 64 messages
Open
worse results when loading with transformers compared to unsloth.fastlangmodel 10 messages
No Module Named Unsloth 3 messages