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

Implement a demo HF wrapper for exllama to utilize existing HF transformers decoding. (#2777)

Browse source
This commit is contained in:
LarryVRH 2023-06-22 02:31:42 +08:00 • committed by GitHub
parent a06acd6d09
commit 580c1ee748
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 101 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/shared.py
View file

@ -98,7 +98,7 @@ parser.add_argument('--extensions', type=str, nargs="+", help='The list of exten
parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
# Model loader
parser.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, llamacpp, rwkv, flexgen')
parser.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, exllama_hf, llamacpp, rwkv, flexgen')
# Accelerate/transformers
parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text. Warning: Training on CPU is extremely slow.')
@ -218,6 +218,8 @@ def fix_loader_name(name):
return 'GPTQ-for-LLaMa'
elif name in ['exllama', 'ex-llama', 'ex_llama', 'exlama']:
return 'ExLlama'
elif name in ['exllama-hf', 'exllama_hf', 'exllama hf', 'ex-llama-hf', 'ex_llama_hf']:
return 'ExLlama_HF'
if args.loader is not None: