llama-recipes

llama-recipes copied to clipboard

Fine-tuning Chat models

3

### 🚀 The feature, motivation and pitch Is there a plan to support fine-tuning for chat models with recommended settings/datasets/data processors etc? ### Alternatives _No response_ ### Additional context _No...

vivekmadan2

Add support to continue pratraining

2

### 🚀 The feature, motivation and pitch Currently the LLaMA-receipts do not support pretraining out of box. For example, one could not save the pretrained model based on the current...

hanyin88

Reasoning behind Alapca's default split

1

For the Alpaca dataset, the default split comprises 51,800 samples for training and 200 samples for testing [1]. What is the rationale behind such a small test set? I haven't...

macsz

When running quickstart.ipynb, loading model in int8 and fp16 occupy significantly different amounts of GPU memory.

1

I am trying finetuning llama2 7B with lora by running quickstart.ipynb(https://github.com/facebookresearch/llama-recipes/blob/main/examples/quickstart.ipynb), using an A100 40G GPU. When I load the model in int8 and create a PeftModel in int8 (just...

lankuohsing

forking repo

1

# What does this PR do? Fixes # (issue) ## Feature/Issue validation/testing Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so...

ajfeigin

Update README.md adding setuptools installation for Mac

1

# What does this PR do? Include a pip install setuptools instruction for MacOS environments ## Before submitting - [ ] This PR fixes a typo or improves the docs...

patrickreinan

Finetuning on a custom dataset

6

### System Info Various versions `2024-01-10 08:35:17 - Successfully installed bitsandbytes-0.39.1 black-23.12.1 brotli-1.1.0 inflate64-1.0.0 llama-recipes-0.0.1 multivolumefile-0.2.3 pathspec-0.12.1 peft-0.6.0.dev0 py7zr-0.20.6 pybcj-1.0.2 pycryptodomex-3.19.1 pyppmd-1.0.0 pyzstd-0.15.9 texttable-1.7.0 tokenize-rt-5.2.0 tomli-2.0.1 torch-2.1.0+cu118 triton-2.1.0` Finetuning command...

pankajtalk

Loss does not converge with FSDP cpu offloading

2

### System Info pytorch==2.2.0 transformers==4.36.2 8 A100 80GB gpus ### Information - [ ] The official example scripts - [X] My own modified scripts ### 🐛 Describe the bug When...

hjlee1371

can't run the RAG_Chatbot_Example.ipynb

1

### System Info Hello, I have issues running the RAG_Chatbot_Example.ipynb notebook. When running the curl command in the notebook, `!curl localhost:8080/generate -X POST -H 'Content-Type: application/json' -d '{"inputs": "What is...

monaalsh

Training running out of memory on 1st backward pass of 2nd epoch

4

### System Info System info ``` Collecting environment information... PyTorch version: 2.1.0+cu118 Is debug build: False CUDA used to build PyTorch: 11.8 ROCM used to build PyTorch: N/A OS: Ubuntu...

mariokostelac