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

6
modules/shared.py
View file

@ -85,7 +85,7 @@ group.add_argument('--chat-buttons', action='store_true', help='Show buttons on
# Model loader
group = parser.add_argument_group('Model loader')
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlama_HF, ExLlamav2_HF, AutoGPTQ, AutoAWQ, GPTQ-for-LLaMa, ExLlama, ExLlamav2, ctransformers, QuIP#.')
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ, GPTQ-for-LLaMa, ctransformers, QuIP#.')
# Transformers/Accelerate
group = parser.add_argument_group('Transformers/Accelerate')
@ -131,7 +131,7 @@ group.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (l
group = parser.add_argument_group('ExLlama')
group.add_argument('--gpu-split', type=str, help='Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.')
group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequence length.')
group.add_argument('--cfg-cache', action='store_true', help='ExLlama_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader, but not necessary for CFG with base ExLlama.')
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('--num_experts_per_token', type=int, default=2, help='Number of experts to use for generation. Applies to MoE models like Mixtral.')
@ -260,8 +260,6 @@ 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'
elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2', 'exllama2', 'exllama-2']:
return 'ExLlamav2'
elif name in ['exllamav2-hf', 'exllamav2_hf', 'exllama-v2-hf', 'exllama_v2_hf', 'exllama-v2_hf', 'exllama2-hf', 'exllama2_hf', 'exllama-2-hf', 'exllama_2_hf', 'exllama-2_hf']: