Merge remote-tracking branch 'refs/remotes/origin/dev' into dev

.gitignore

@@ -26,6 +26,7 @@
 .DS_Store
 .eslintrc.js
 .idea
+.env
 .venv
 venv
 .vscode

models/config.yaml

@@ -45,9 +45,6 @@
 .*starchat-beta:
   instruction_template: 'Starchat-Beta'
   custom_stopping_strings: '"<|end|>"'
-.*(openorca-platypus2):
-  instruction_template: 'OpenOrca-Platypus2'
-  custom_stopping_strings: '"### Instruction:", "### Response:"'
 (?!.*v0)(?!.*1.1)(?!.*1_1)(?!.*stable)(?!.*chinese).*vicuna:
   instruction_template: 'Vicuna-v0'
 .*vicuna.*v0:
@@ -152,6 +149,9 @@
   instruction_template: 'Orca Mini'
 .*(platypus|gplatty|superplatty):
   instruction_template: 'Alpaca'
+.*(openorca-platypus2):
+  instruction_template: 'OpenOrca-Platypus2'
+  custom_stopping_strings: '"### Instruction:", "### Response:"'
 .*longchat:
   instruction_template: 'Vicuna-v1.1'
 .*vicuna-33b:

modules/GPTQ_loader.py

@@ -62,7 +62,7 @@ def noop(*args, **kwargs):
         from safetensors.torch import load_file as safe_load
         model.load_state_dict(safe_load(checkpoint), strict=False)
     else:
-        model.load_state_dict(torch.load(checkpoint), strict=False)
+        model.load_state_dict(torch.load(checkpoint, weights_only=True), strict=False)
 
     model.seqlen = 2048
     return model

modules/training.py

@@ -544,7 +544,7 @@ def generate_and_tokenize_prompt(data_point):
         lora_model = get_peft_model(shared.model, config)
         if not always_override and Path(f"{lora_file_path}/adapter_model.bin").is_file():
             logger.info("Loading existing LoRA data...")
-            state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin")
+            state_dict_peft = torch.load(f"{lora_file_path}/adapter_model.bin", weights_only=True)
             set_peft_model_state_dict(lora_model, state_dict_peft)
     except:
         yield traceback.format_exc().replace('\n', '\n\n')