llama
llama copied to clipboard
Inference code for Llama models
Post your funny or interesting results of the language model here. 😁
Good news people. Neural Network Weights are not copyrightable by US law. `"that material from a non-human entity is not copyrightable"` Also, since the model itself is open-source, this means...
I have reimplemented llama with the paddlepaddle framework and provided an example of running 7b using aistudio free computing power, feel free to test and suggest improvements. repo: [ppllama](https://github.com/MiuGod0126/ppllama)
Being a grad student, I have limited free personal resources such as Google Colab available. But in Google Colab, when I try running the `example.py` script (after downloading weights), I...
I encountered an error when running torchrun command on my system with the following traceback: ``` Traceback (most recent call last): File "/mnt/f/projects/python/git/llama/venv/bin/torchrun", line 8, in sys.exit(main()) ^^^^^^ File "/mnt/f/projects/python/git/llama/venv/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py",...
Thanks for sharing this really good material. I have a lot of questions. First, I'd like to say that I hope you ignore much of the mockery. Everyone, including me,...
Can someone please seed the llama weights at magnet:?xt=urn:btih:b8287ebfa04f879b048d4d4404108cf3e8014352&dn=LLaMA&tr=udp%3a%2f%2ftracker.opentrackr.org%3a1337%2fannounce Or make them availabe at google drive? There are 0 seeders not sure how long they will stay
Hi, I've been trying to run the example inference using the 7B model weights, but I get: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0; 39.59...
I am trying to run inference on the 7B parameter model on 4x2080Ti, the default script to run inference gives me a CUDA OOM error. is there a way to...
RuntimeError: CUDA out of memory. Tried to allocate 160.00 MiB (GPU 0; 15.78 GiB total capacity; 14.26 GiB already allocated; 121.19 MiB free; 14.69 GiB reserved in total by PyTorch)...