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

Bump llama-cpp-python

Browse source
This commit is contained in:
oobabooga 2023-08-17 21:39:26 -07:00
parent 3e7c624f8e
commit 6170b5ba31
7 changed files with 21 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
modules/llamacpp_hf.py
View file

@ -102,6 +102,12 @@ class LlamacppHF(PreTrainedModel):
model_file = list(path.glob('*ggml*.bin'))[0]
logger.info(f"llama.cpp weights detected: {model_file}\n")
if shared.args.tensor_split is None or shared.args.tensor_split.strip() == '':
tensor_split_list = None
else:
tensor_split_list = [float(x) for x in shared.args.tensor_split.strip().split(",")]
params = {
'model_path': str(model_file),
'n_ctx': shared.args.n_ctx,
@ -113,6 +119,7 @@ class LlamacppHF(PreTrainedModel):
'low_vram': shared.args.low_vram,
'n_gpu_layers': shared.args.n_gpu_layers,
'rope_freq_base': 10000 * shared.args.alpha_value ** (64 / 63.),
'tensor_split': tensor_split_list,
'rope_freq_scale': 1.0 / shared.args.compress_pos_emb,
'n_gqa': shared.args.n_gqa or None,
'rms_norm_eps': shared.args.rms_norm_eps or None,