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

Falcon support (trust-remote-code and autogptq checkboxes) (#2367)

Browse source 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
This commit is contained in:
Honkware 2023-05-29 08:20:18 -05:00 • committed by GitHub
parent 60ae80cf28
commit 204731952a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/AutoGPTQ_loader.py
View file

@ -35,6 +35,7 @@ def load_quantized(model_name):
'device': "cuda:0" if not shared.args.cpu else "cpu",
'use_triton': shared.args.triton,
'use_safetensors': use_safetensors,
'trust_remote_code': shared.args.trust_remote_code,
'max_memory': get_max_memory_dict()
}

2
modules/shared.py
View file

@ -110,7 +110,7 @@ parser.add_argument('--bf16', action='store_true', help='Load the model with bfl
parser.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces the VRAM usage a bit at a performance cost.')
parser.add_argument('--xformers', action='store_true', help="Use xformer's memory efficient attention. This should increase your tokens/s.")
parser.add_argument('--sdp-attention', action='store_true', help="Use torch 2.0's sdp attention.")
parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM.")
parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon.")
# Accelerate 4-bit
parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision (using bitsandbytes).')

2
modules/ui.py
View file

@ -30,7 +30,7 @@ theme = gr.themes.Default(
def list_model_elements():
elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'trust_remote_code', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'autogptq', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
for i in range(torch.cuda.device_count()):
elements.append(f'gpu_memory_{i}')