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

Remove exllamav1 loaders (#5128)

Browse source
This commit is contained in:
oobabooga 2023-12-31 01:57:06 -03:00 • committed by GitHub
parent 8e397915c9
commit 0e54a09bcb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
18 changed files with 28 additions and 635 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/text_generation.py
View file

@ -44,7 +44,7 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
yield ''
return
if shared.model.__class__.__name__ in ['LlamaCppModel', 'RWKVModel', 'ExllamaModel', 'Exllamav2Model', 'CtransformersModel']:
if shared.model.__class__.__name__ in ['LlamaCppModel', 'RWKVModel', 'Exllamav2Model', 'CtransformersModel']:
generate_func = generate_reply_custom
else:
generate_func = generate_reply_HF
@ -132,7 +132,7 @@ def encode(prompt, add_special_tokens=True, add_bos_token=True, truncation_lengt
if truncation_length is not None:
input_ids = input_ids[:, -truncation_length:]
if shared.model.__class__.__name__ in ['LlamaCppModel', 'RWKVModel', 'ExllamaModel', 'Exllamav2Model', 'CtransformersModel'] or shared.args.cpu:
if shared.model.__class__.__name__ in ['LlamaCppModel', 'RWKVModel', 'Exllamav2Model', 'CtransformersModel'] or shared.args.cpu:
return input_ids
elif shared.args.deepspeed:
return input_ids.to(device=local_rank)