mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #224 from ItsLogic/llama-bits

Browse source 
Allow users to load 2, 3 and 4 bit llama models
This commit is contained in:
oobabooga 2023-03-12 11:23:50 -03:00 • committed by GitHub
commit f3b00dd165
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 67 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -69,6 +69,7 @@ parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI i
parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.')
parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.')
parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision. Currently only works with LLaMA.')
parser.add_argument('--gptq-bits', type=int, default=0, help='Load a pre-quantized model with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA.')
parser.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.')
parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')