forum
Ollama Modelfile issues
Support for Llava
torch.compile Torch 2.3 + Xformers
Galore + QLoRA
Reserved Tokens Appears Llama-3
Error ORPO training
Solved
How do I... use non alpaca formats??
Open
Advice for training Llama3 on a new coding laungage
Assertion error Llama 3
Open
What is context size?
Open
Add\Remove data to model
How to fine-tune an LLM for languages other than English
Open
Kaggle storage limitations
Open
Fine Tune Llama3 Inference Works On Colab - GGUF produces garbage results in LMstudio.
0 bytes gguf files as push_to_hub_gguf
Open
ChatML Save error
Open
Dataset Format
Open
Implement from_config method
Open
Why is llama 3 new prompt template different from the one in the finetuning colab?
Open
I'm completely stuck: llama3 Instruct - Infinite generation issues, agent framework
Solved
LLAMA3 Tokenizer and prompt format issues
Solved
Save from specific checkpoints
Solved
AttributeError: module 'torch.utils._pytree' has no attribute 'register_pytree_node'
Issue using load_in_8bit with Unsloth library
Solved
Build Translation Model
Open
GGUF conversion llama.cpp error code = 2
Open
Issue with Llama 3 Finetuning?
Open
Massive memory usage adding "lm_head" to Llama3
Open
Special tokens have been added...
bug when loading the llama3 instruct model
Open
Advice on fine tuning TinyLLama on small dataset
Open
WSL help for @Hueman Instrument
Solved
Llama3 fine-tune got error 'PreTrainedTokenizerFast' object has no attribute 'add_bos_token'
Open
Is it possible to run unsloth in a K80 GPU?
Open
Target all modules
Solved
Saving GGUF Model llama3 collab
Solved
Downloading GGUF model
Solved
save_pretrained_gguf on databricks
Open
About finetuning and uploading 13B model in Colab
Solved
How to build a good dataset ?
Open
can't make a working dataset
Solved
Good Idea to add new token?
Open
Fine-tune LLM for chatbot
Solved
RuntimeError: Mismatched Data Types with BFloat16 and float during Fine-Tuning
Solved
Corrupted Vocab
Open
Error on resuming training from checkpoints
Solved
Resuming Training
Solved
Using LLM locally
Open
Tried everything to save Gemma-2b-it (in 4 bit from unsloth and also directly fromt google)
Open
Issue when continuing training (FastLanguageModel.from_pretrained)
Solved