pyllama

pyllama copied to clipboard

evaluating has an extremely large value when quantize to 4bit.

1

I followed the steps try to get 4bit version of llama7b by using command `python -m llama.llama_quant decapoda-research/llama-7b-hf c4 --wbits 4 --groupsize 128 --save pyllama-7B4b.pt`, the script works well, but...

JiachuanDENG

aria2c 'magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA' not working

1

Pls see the title. I can't download checkpoints and tokenizer. I get the following *** Download Progress Summary as of Sat Apr 22 12:43:53 2023 *** ===================================================================================== [#b77f54 0B/0B CN:1...

Nolyzlel

Added tranformers for #67

HireTheHero

ModuleNotFoundError: No module named 'transformers'

6

Anyone else experienced this? When running: `python -m llama.download --model_size 7B` Error log shows: `Traceback (most recent call last): File "/Users/willbeing/miniconda/envs/test_snakes/lib/python3.9/runpy.py", line 188, in _run_module_as_main mod_name, mod_spec, code = _get_module_details(mod_name,...

tasteitslight

when use ` python quant_infer.py --wbits 2 --load pyllama-7B8b.pt --text "..." --max_length 24 ` , it raises error `NVMLError_NoPermission: Insufficient Permissions`

sz2three

Hi, I'm having difficulties downloading the files. I solved all the repeating downloads, but encountered a new one. Now it actually does start the download, but something kicks in and...

kryt

Cannot run on Mac with Python 3.11.3

6

python3 -m llama.download --model_size 7B Traceback (most recent call last): File "/opt/homebrew/lib/python3.11/site-packages/itree/__init__.py", line 5, in from . import _itree ImportError: cannot import name '_itree' from partially initialized module 'itree' (most...

kornhill

Downloading get stuck in infinite loop

13

When trying to download the models, I get stuck in some infinite loop. This repeats once every second until I terminate the program. Environment: * pyllama version: `commit 321d475f01c88e179c8a30d68b5281e2caca5b07 (HEAD...

jarimustonen

when I run "python ./pyllama/quant_infer.py --wbits 4 --load ./output/654b.pt --text "what is life" --max_length 24 --cuda cuda:0" , I got the error below. I converted llama 65B into 4int, with...

ZealHua

RecursionError running llama.download

4

I am using python3.8.5, and installed all dependencies from both requirements files. Then run `python -m llama.download --model_size 7B`, got the following error message ``` File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/subprocess.py", line 854, in...

anyangpeng