mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-04-05 06:35:15 +00:00
Add ExLlamaV3 support (#6832)
This commit is contained in:
parent
0b3503c91f
commit
8b8d39ec4e
13 changed files with 322 additions and 54 deletions
|
|
@ -86,7 +86,7 @@ group.add_argument('--idle-timeout', type=int, default=0, help='Unload model aft
|
|||
|
||||
# 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, ExLlamav2, HQQ, TensorRT-LLM.')
|
||||
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2, HQQ, TensorRT-LLM.')
|
||||
|
||||
# Transformers/Accelerate
|
||||
group = parser.add_argument_group('Transformers/Accelerate')
|
||||
|
|
@ -273,6 +273,8 @@ def fix_loader_name(name):
|
|||
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 ['exllamav3-hf', 'exllamav3_hf', 'exllama-v3-hf', 'exllama_v3_hf', 'exllama-v3_hf', 'exllama3-hf', 'exllama3_hf', 'exllama-3-hf', 'exllama_3_hf', 'exllama-3_hf']:
|
||||
return 'ExLlamav3_HF'
|
||||
elif name in ['hqq']:
|
||||
return 'HQQ'
|
||||
elif name in ['tensorrt', 'tensorrtllm', 'tensorrt_llm', 'tensorrt-llm', 'tensort', 'tensortllm']:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue