llama
llama copied to clipboard
Inference code for Llama models
**Before submitting a bug, please make sure the issue hasn't been already addressed by searching through the [FAQs](https://ai.meta.com/llama/faq/) and [existing/past issues](https://github.com/facebookresearch/llama/issues)** ## Describe the bug I'm following steps listed here...
Hi everybody, I tried to deploy the llama2 model in pytorch/CUDA env: CUDA version: 12.1 ID of current CUDA device: 0 Name of current CUDA device: Quadro P4000 but I...
I am having trouble running inference on the 70b model as it is using additional CPU memory, possibly creating a bottleneck in performance. It is unable to load all 70b...
self-explanatory. i'm just running download script, pasting it url from e-mail, and get only couple small config files. no shards are downloaded, no errors are reported either.
my code: import os os.environ['CUDA_VISIBLE_DEVICES'] = '0' import torch from accelerate import Accelerator from accelerate.utils import set_seed from transformers import LlamaForCausalLM, LlamaTokenizer, LlamaConfig set_seed(1234) prefix_path = '/home/xsong/llama/Llama-2-7b-hf' accelerator = Accelerator()...
I get this error in VSCode: Cannot import KnowledgeBase from llama2 (/data/../Site-packages/llama2/__init__.py) The directory has this content: -rw-rw-r-- 1 pgraf pgraf 2 Feb 28 17:10 __init__.py drwxrwxr-x 2 pgraf pgraf...
This is my sample pull request
As a PhD student, I have applied to access the llama model and I couldn't get any response for nearly a week. In the Hugging Face, it says " Requests...
**Before submitting a bug, please make sure the issue hasn't been already addressed by searching through the [FAQs](https://ai.meta.com/llama/faq/) and [existing/past issues](https://github.com/facebookresearch/llama/issues)** ## Describe the bug ![image](https://github.com/facebookresearch/llama/assets/67573223/71bc9b05-d81e-40df-8bc2-cdce1e7f5538) I have got ssl...
**Before submitting a bug, please make sure the issue hasn't been already addressed by searching through the [FAQs](https://ai.meta.com/llama/faq/) and [existing/past issues](https://github.com/facebookresearch/llama/issues)** ## Describe the bug ### Minimal reproducible example ```python...