forum

1495 threads · Page 29 of 30

Ollama Modelfile issues 2 messages
Support for Llava 4 messages
torch.compile Torch 2.3 + Xformers 6 messages
Galore + QLoRA 2 messages
Reserved Tokens Appears Llama-3 4 messages
Error ORPO training 5 messages
Solved
How do I... use non alpaca formats?? 7 messages
Open
Advice for training Llama3 on a new coding laungage 5 messages
Assertion error Llama 3 4 messages
Open
What is context size? 6 messages
Open
Add\Remove data to model 2 messages
How to fine-tune an LLM for languages other than English 9 messages
Open
Kaggle storage limitations 7 messages
Open
Fine Tune Llama3 Inference Works On Colab - GGUF produces garbage results in LMstudio. 436 messages
0 bytes gguf files as push_to_hub_gguf 3 messages
Open
ChatML Save error 4 messages
Open
Dataset Format 3 messages
Open
Implement from_config method 2 messages
Open
Why is llama 3 new prompt template different from the one in the finetuning colab? 21 messages
Open
I'm completely stuck: llama3 Instruct - Infinite generation issues, agent framework 91 messages
Solved
LLAMA3 Tokenizer and prompt format issues 34 messages
Solved
Save from specific checkpoints 47 messages
Solved
AttributeError: module 'torch.utils._pytree' has no attribute 'register_pytree_node' 7 messages
Issue using load_in_8bit with Unsloth library 2 messages
Solved
Build Translation Model 5 messages
Open
GGUF conversion llama.cpp error code = 2 38 messages
Open
Issue with Llama 3 Finetuning? 3 messages
Open
Massive memory usage adding "lm_head" to Llama3 11 messages
Open
Special tokens have been added... 2 messages
bug when loading the llama3 instruct model 5 messages
Open
Advice on fine tuning TinyLLama on small dataset 24 messages
Open
WSL help for @Hueman Instrument 1111 messages
Solved
Llama3 fine-tune got error 'PreTrainedTokenizerFast' object has no attribute 'add_bos_token' 16 messages
Open
Is it possible to run unsloth in a K80 GPU? 15 messages
Open
Target all modules 22 messages
Solved
Saving GGUF Model llama3 collab 12 messages
Solved
Downloading GGUF model 2 messages
Solved
save_pretrained_gguf on databricks 8 messages
Open
About finetuning and uploading 13B model in Colab 12 messages
Solved
How to build a good dataset ? 2 messages
Open
can't make a working dataset 12 messages
Solved
Good Idea to add new token? 9 messages
Open
Fine-tune LLM for chatbot 2 messages
Solved
RuntimeError: Mismatched Data Types with BFloat16 and float during Fine-Tuning 10 messages
Solved
Corrupted Vocab 13 messages
Open
Error on resuming training from checkpoints 3 messages
Solved
Resuming Training 8 messages
Solved
Using LLM locally 3 messages
Open
Tried everything to save Gemma-2b-it (in 4 bit from unsloth and also directly fromt google) 6 messages
Open
Issue when continuing training (FastLanguageModel.from_pretrained) 10 messages
Solved