Merge Latest Frontier (#1991)

* logging sys to loguru: stage 1 complete

* import loguru: stage 2

* logging -> loguru: stage 3

* support o1-preview and o1-mini

* logging -> loguru stage 4

* update social helper

* logging -> loguru: final stage

* fix: console output

* update translation matrix

* fix: loguru argument error with proxy enabled (#1977)

* relax llama index version

* remove comment

* Added some modules to support openrouter (#1975)

* Added some modules for supporting openrouter model

Added some modules for supporting openrouter model

* Update config.py

* Update .gitignore

* Update bridge_openrouter.py

* Not changed actually

* Refactor logging in bridge_openrouter.py

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* remove logging extra

---------

Co-authored-by: Steven Moder <java20131114@gmail.com>
Co-authored-by: Ren Lifei <2602264455@qq.com>

request_llms/bridge_chatglmft.py

@@ -1,12 +1,13 @@
 
 from transformers import AutoModel, AutoTokenizer
+from loguru import logger
+from toolbox import update_ui, get_conf
+from multiprocessing import Process, Pipe
 import time
 import os
 import json
 import threading
 import importlib
-from toolbox import update_ui, get_conf
-from multiprocessing import Process, Pipe
 
 load_message = "ChatGLMFT尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，ChatGLMFT消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
 
@@ -78,7 +79,7 @@ class GetGLMFTHandle(Process):
                     config.pre_seq_len = model_args['pre_seq_len']
                     config.prefix_projection = model_args['prefix_projection']
 
-                    print(f"Loading prefix_encoder weight from {CHATGLM_PTUNING_CHECKPOINT}")
+                    logger.info(f"Loading prefix_encoder weight from {CHATGLM_PTUNING_CHECKPOINT}")
                     model = AutoModel.from_pretrained(model_args['model_name_or_path'], config=config, trust_remote_code=True)
                     prefix_state_dict = torch.load(os.path.join(CHATGLM_PTUNING_CHECKPOINT, "pytorch_model.bin"))
                     new_prefix_state_dict = {}
@@ -88,7 +89,7 @@ class GetGLMFTHandle(Process):
                     model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
 
                     if model_args['quantization_bit'] is not None and model_args['quantization_bit'] != 0:
-                        print(f"Quantized to {model_args['quantization_bit']} bit")
+                        logger.info(f"Quantized to {model_args['quantization_bit']} bit")
                         model = model.quantize(model_args['quantization_bit'])
                     model = model.cuda()
                     if model_args['pre_seq_len'] is not None: