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

Add support for the latest GPTQ models with group-size (#530)

Browse source 
**Warning: old 4-bit weights will not work anymore!**

See here how to get up to date weights: https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model#step-2-get-the-pre-converted-weights
This commit is contained in:
oobabooga 2023-03-26 00:11:33 -03:00 • committed by GitHub
parent 8c8e8b4450
commit 49c10c5570
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 64 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

24
modules/shared.py
View file

@ -52,7 +52,8 @@ settings = {
'default': 'Common sense questions and answers\n\nQuestion: \nFactual answer:',
'^(gpt4chan|gpt-4chan|4chan)': '-----\n--- 865467536\nInput text\n--- 865467537\n',
'(rosey|chip|joi)_.*_instruct.*': 'User: \n',
'oasst-*': '<|prompter|>Write a story about future of AI development<|endoftext|><|assistant|>'
'oasst-*': '<|prompter|>Write a story about future of AI development<|endoftext|><|assistant|>',
'alpaca-*': "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n### Instruction:\nWrite a poem about the transformers Python library. \nMention the word \"large language models\" in that poem.\n### Response:\n",
},
'lora_prompts': {
'default': 'Common sense questions and answers\n\nQuestion: \nFactual answer:',
@ -78,10 +79,15 @@ parser.add_argument('--chat', action='store_true', help='Launch the web UI in ch
parser.add_argument('--cai-chat', action='store_true', help='Launch the web UI in chat mode with a style similar to Character.AI\'s. If the file img_bot.png or img_bot.jpg exists in the same folder as server.py, this image will be used as the bot\'s profile picture. Similarly, img_me.png or img_me.jpg will be used as your profile picture.')
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='DEPRECATED: use --gptq-bits 4 instead.')
parser.add_argument('--gptq-bits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision. 2, 3, 4 and 8bit are supported. Currently only works with LLaMA and OPT.')
parser.add_argument('--gptq-model-type', type=str, help='GPTQ: Model type of pre-quantized model. Currently only LLaMa and OPT are supported.')
parser.add_argument('--gptq-pre-layer', type=int, default=0, help='GPTQ: The number of layers to preload.')
parser.add_argument('--gptq-bits', type=int, default=0, help='DEPRECATED: use --wbits instead.')
parser.add_argument('--gptq-model-type', type=str, help='DEPRECATED: use --model_type instead.')
parser.add_argument('--gptq-pre-layer', type=int, default=0, help='DEPRECATED: use --pre_layer instead.')
parser.add_argument('--wbits', type=int, default=0, help='GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
parser.add_argument('--model_type', type=str, help='GPTQ: Model type of pre-quantized model. Currently only LLaMA and OPT are supported.')
parser.add_argument('--groupsize', type=int, default=-1, help='GPTQ: Group size.')
parser.add_argument('--pre_layer', type=int, default=0, help='GPTQ: The number of layers to preload.')
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.')
@ -109,6 +115,8 @@ parser.add_argument('--verbose', action='store_true', help='Print the prompts to
args = parser.parse_args()
# Provisional, this will be deleted later
if args.load_in_4bit:
print("Warning: --load-in-4bit is deprecated and will be removed. Use --gptq-bits 4 instead.\n")
args.gptq_bits = 4
deprecated_dict = {'gptq_bits': ['wbits', 0], 'gptq_model_type': ['model_type', None], 'gptq_pre_layer': ['prelayer', 0]}
for k in deprecated_dict:
if eval(f"args.{k}") != deprecated_dict[k][1]:
print(f"Warning: --{k} is deprecated and will be removed. Use --{deprecated_dict[k][0]} instead.")
exec(f"args.{deprecated_dict[k][0]} = args.{k}")