llama-recipes

llama-recipes copied to clipboard

load_model failed

1

### System Info [pip3] flake8==7.0.0 [pip3] flake8-bugbear==24.2.6 [pip3] mypy-extensions==1.0.0 [pip3] numpy==1.26.4 [pip3] torch==2.2.1+cu118 [pip3] torchdata==0.7.1+cpu [pip3] torchtext==0.17.1 [pip3] triton==2.2.0 [conda] numpy 1.26.4 pypi_0 pypi [conda] torch 2.2.1+cu118 pypi_0 pypi [conda]...

wygao8

Should we adjust attention mask when packing data?

2

### 🚀 The feature, motivation and pitch Hello, I am hoping to seek some guidance on a common scenario. I am wondering when selecting "packing" (instead of padding) as the...

hanyin88

ValueError: Transformers now supports natively BetterTransformer optimizations

3

ValueError: Transformers now supports natively BetterTransformer optimizations (torch.nn.functional.scaled_dot_product_attention) for the model type llama. As such, there is no need to use `model.to_bettertransformers()` or `BetterTransformer.transform(model)` from the Optimum library. Please upgrade...

huangjf11

Make predictions based on historical data CSV file?

2

I'd appreciate some advice on a problem, since I don't have expertise in AI or Data Science. I need to analyze historical data to build a forecasting model, using a...

marcelooliveira

Quickstart notebook breaking

4

### System Info Pytorch=2.1.0, CUDA=11.8, GPU=a10g (24 GB), Num of GPUs=1 ### Information - [x] The official example scripts - [ ] My own modified scripts ### 🐛 Describe the...

Nomiizz

I'm a computer novice, and when fine-tuning using the google/civil_comments dataset, I implemented another preprocessing function modeled after get_preprocessed_samsum, but I kept having problems. Can you help me find out...

yuhkalhic

Fine tune on domain dataset and convert it as a chat based model

3

Hi team, I would like to fine tune Llama2 model with my domain data and eventually convert it as a chat model. so, I can directly ask questions related to...

IamExperimenting

Question about ‘labels’

2

Hi, thanks for your great work! I'm using the code in the llama-recipes repository to fine-tune my own data and have a question for you: I read the examples/quickstart.ipynb code,...

SatireY

How to finetune with a own private data and then build chatbot on that?

3

So far with the example of fine tuning I see examples of summarisation, chatbot based on specific use cases etc. However, I want to build the a chatbot based on...

rjtshrm

Support for AMD GPUs in the Llama Recipes notebook quickstart

3

### 🚀 The feature, motivation and pitch So I'm using an RX 7900 XTX with PyTorch 2.2.0.dev20231005+rocm5.7. From the error message below, it seems that it's a problem with bitsandbytes...

PatchouliPatch