Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 18:45:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

llama.cpp: default n_gpu_layers to the maximum value for the model automatically

Browse source
This commit is contained in:
oobabooga 2024-05-19 10:57:42 -07:00
parent a4611232b7
commit a38a37b3b3
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
modules/models_settings.py
View file

@ -56,6 +56,7 @@ def get_model_metadata(model):
model_file = list(path.glob('*.gguf'))[0] model_file = list(path.glob('*.gguf'))[0]
metadata = metadata_gguf.load_metadata(model_file) metadata = metadata_gguf.load_metadata(model_file)
for k in metadata: for k in metadata:
if k.endswith('context_length'): if k.endswith('context_length'):
model_settings['n_ctx'] = metadata[k] model_settings['n_ctx'] = metadata[k]
@ -63,6 +64,9 @@ def get_model_metadata(model):
model_settings['rope_freq_base'] = metadata[k] model_settings['rope_freq_base'] = metadata[k]
elif k.endswith('rope.scale_linear'): elif k.endswith('rope.scale_linear'):
model_settings['compress_pos_emb'] = metadata[k] model_settings['compress_pos_emb'] = metadata[k]
elif k.endswith('block_count'):
model_settings['n_gpu_layers'] = metadata[k] + 1
if 'tokenizer.chat_template' in metadata: if 'tokenizer.chat_template' in metadata:
template = metadata['tokenizer.chat_template'] template = metadata['tokenizer.chat_template']
eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']] eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]