diff --git a/api-examples/api-example-model.py b/api-examples/api-example-model.py index 9a61ccb1..44109d36 100644 --- a/api-examples/api-example-model.py +++ b/api-examples/api-example-model.py @@ -108,7 +108,7 @@ def complex_model_load(model): req['args']['bf16'] = True # for 24GB elif '13b' in model: req['args']['load_in_8bit'] = True # for 24GB - elif 'ggml' in model: + elif 'gguf' in model: # req['args']['threads'] = 16 if '7b' in model: req['args']['n_gpu_layers'] = 100 diff --git a/download-model.py b/download-model.py index 1c449683..ba4d3bc7 100644 --- a/download-model.py +++ b/download-model.py @@ -125,7 +125,7 @@ class ModelDownloader: if base_folder is None: base_folder = 'models' if not is_lora else 'loras' - # If the model is of type GGUF or GGML, save directly in the base_folder + # If the model is of type GGUF, save directly in the base_folder if is_llamacpp: return Path(base_folder) diff --git a/modules/exllama.py b/modules/exllama.py index 12c4c02c..c9ff1228 100644 --- a/modules/exllama.py +++ b/modules/exllama.py @@ -3,7 +3,7 @@ from pathlib import Path import torch.nn.functional as F from torch import version as torch_version -from modules import RoPE, shared +from modules import shared from modules.logging_colors import logger from modules.models import clear_torch_cache from modules.text_generation import get_max_prompt_length diff --git a/modules/exllama_hf.py b/modules/exllama_hf.py index 81ba1cb7..9e4701bf 100644 --- a/modules/exllama_hf.py +++ b/modules/exllama_hf.py @@ -7,7 +7,7 @@ from torch.nn import CrossEntropyLoss from transformers import GenerationConfig, PretrainedConfig, PreTrainedModel from transformers.modeling_outputs import CausalLMOutputWithPast -from modules import RoPE, shared +from modules import shared from modules.logging_colors import logger try: