Lint

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

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)
 

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

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: