forum

1495 threads · Page 28 of 30

How to install unsloth in kaggle? 2 messages
Solved
Increasing batch size doesn't decrease time 5 messages
Solved
Training stops with no errors 6 messages
Solved
error integer dtype tensors in FSPD 5 messages
Error an illegal memory access 2 messages
Open
I got xFormers wasn't build with CUDA support. 13 messages
Need someone who can help fine-tuning Stable Diffusion and using ControlNet? 2 messages
Open
Chat template being pushed into tokenizer for phi-3 mini but not Llama 3 13 messages
Solved
4bit model creation 7 messages
Open
Model repeating 10 messages
Open
Any downsides in fine-turning models with non-proprietary chat templates? 5 messages
Solved
Question changed promt format and now geting bad results 16 messages
Open
Potential bug in Mistralv3 (kaggle) notebook 36 messages
2x T4 GPU 6 messages
Performance comparison with axolotl 21 messages
Solved
Evaluation dataset 2 messages
Solved
Memory spikes on text completion lang dataset 17 messages
Open
cloudflare ai 6 messages
Open
How to handle "" in the dataset 9 messages
Open
Anyone got unsloth working on sagemaker studio lab? 5 messages
Ollama setup for @omar 14 messages
Guides on converting an LLM to GGUF 4 messages
Upload a Lora checkpoint to huggingface 4 messages
Mix of Dataset 4 messages
Open
Saving models 3 messages
GGUF Quantizing 10 messages
Fine Tuned Llama3-8B inference repetition issue 8 messages
Open
Llama-3 example SFT notebook on Databricks > flash attention error 13 messages
Open
Fine Tune on Intel GPU 10 messages
Minimum Requirements 6 messages
Model tags wrong 8 messages
How to get the response only and a GGUF question 11 messages
Multiple datasets 5 messages
Trying to fine-tune LLaMa-70B on an 8xA100 (40GB Cluster) 21 messages
Datasets for Chat Format 4 messages
Train on Completions 13 messages
ORPOTrainer consuming much more memory than SFTTrainer 5 messages
Solved
NaNs while finetuning llama3 8b instruct model 2 messages
Open
Unsloth supported by fireworks AI? 9 messages
Is there a Unsloth roadmap? 4 messages
Index Out of Bounds Error 8 messages
Open
Training loss not going down- saving tuned model to HF as full .safetensor model. 4 messages
Build Conversational chatbot 6 messages
Open
Error when using tensordock (pytorch) suppose to be supported) 39 messages
Can't convert finetuned llm to gguf file 14 messages
ValueError: expected sequence of length "X" at dim 1 (got "Y") 5 messages
Open
<|end_of_text|> instead of <|eot_token|> 42 messages
Issues with inference on large input on llama 3 8B fine tuning 4 messages
GGUF accuracy drops 3 messages
Bitsandbytes not installing on H100 19 messages