oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 14:17:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update cache_4bit documentation (#5649)

Browse source 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
This commit is contained in:
Bartowski 2024-03-07 11:08:21 -05:00 • committed by GitHub
parent bef08129bc
commit 104573f7d4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -139,7 +139,7 @@ group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequen
group.add_argument('--cfg-cache', action='store_true', help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')
group.add_argument('--cache_8bit', action='store_true', help='Use 8-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use 4-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use Q4 cache to save VRAM.')
group.add_argument('--num_experts_per_token', type=int, default=2, help='Number of experts to use for generation. Applies to MoE models like Mixtral.')
# AutoGPTQ