oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-07 15:43:49 +00:00
Code Issues Projects Releases Packages Wiki Activity

Revert "Remove non-HF ExLlamaV2 loader (#5431)"

Browse source 
This reverts commit cde000d478.
This commit is contained in:
oobabooga 2024-02-06 06:21:17 -08:00
parent 8c35fefb3b
commit 2a1063eff5
9 changed files with 220 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

14
modules/shared.py
View file

@ -89,7 +89,7 @@ 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, ExLlamav2_HF, AutoGPTQ, AutoAWQ, GPTQ-for-LLaMa, 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')
@ -132,11 +132,11 @@ group.add_argument('--no_offload_kqv', action='store_true', help='Do not offload
group.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
group.add_argument('--row_split', action='store_true', help='Split multi-gpu by row instead of layer. Faster on some cards.')
# ExLlamaV2
group = parser.add_argument_group('ExLlamaV2')
# ExLlama
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='Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
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.')
@ -250,7 +250,11 @@ def fix_loader_name(name):
return 'AutoGPTQ'
elif name in ['gptq-for-llama', 'gptqforllama', 'gptqllama', 'gptq for llama', 'gptq_for_llama']:
return 'GPTQ-for-LLaMa'
elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2', 'exllama2', 'exllama-2', 'exllama', 'ex-llama', 'ex_llama', 'exlama', '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']:
elif name in ['exllama', 'ex-llama', 'ex_llama', 'exlama']:
return 'ExLlama'
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']:
return 'ExLlamav2_HF'
elif name in ['ctransformers', 'ctranforemrs', 'ctransformer']:
return 'ctransformers'