Fixed req file

.gitignore

@@ -1,14 +1,7 @@
-># Environment files
-.env
-.env.*
-
 # Virtual environment
 myenv/
 venv/
-ENV/
-
-# Model checkpoints
-checkpoints/
+env/
 
 # Python
 __pycache__/
@@ -16,30 +9,24 @@ __pycache__/
 *$py.class
 *.so
 .Python
-build/
-develop-eggs/
+*.egg
+*.egg-info/
 dist/
-downloads/
+build/
 eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
 *.egg-info/
-.installed.cfg
-*.egg
+.eggs/
+
+# Models
+models/
+main/models/
 
 # IDE
-.idea/
 .vscode/
+.idea/
 *.swp
-*.swo
-.DS_Store
+*~
 
-# Logs
-*.log
-logs/
-.cache/
+# OS
+.DS_Store
+Thumbs.db

main/logs/llm_api.log

@@ -0,0 +1,19 @@
+2025-01-09 15:54:08,215 - hf_validation - WARNING - No .env file found. Fine if you're on Huggingface, but you need one to run locally on your PC.
+2025-01-09 15:54:08,215 - hf_validation - ERROR - No HF_TOKEN found in environment variables
+2025-01-09 15:54:08,215 - main - INFO - Starting LLM API server
+2025-01-09 15:54:08,216 - llm_api - INFO - Initializing LLM API
+2025-01-09 15:54:08,216 - llm_api - INFO - LLM API initialized successfully
+2025-01-09 15:54:08,216 - api_routes - INFO - Router initialized with LLM API instance
+2025-01-09 15:54:08,218 - main - INFO - FastAPI application created successfully
+2025-01-09 16:46:10,118 - api_routes - INFO - Received request to download model: microsoft/phi-4
+2025-01-09 16:46:10,118 - llm_api - INFO - Starting download of model: microsoft/phi-4
+2025-01-09 16:46:10,118 - llm_api - INFO - Enabling stdout logging for download
+2025-01-09 17:00:32,400 - llm_api - INFO - Disabling stdout logging
+2025-01-09 17:00:32,400 - llm_api - INFO - Saving model to main/models/phi-4
+2025-01-09 17:02:39,928 - llm_api - INFO - Successfully downloaded model: microsoft/phi-4
+2025-01-09 17:02:41,075 - api_routes - INFO - Successfully downloaded model: microsoft/phi-4
+2025-01-09 17:02:41,080 - api_routes - INFO - Received request to initialize model: huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+2025-01-09 17:02:41,080 - llm_api - INFO - Initializing generation model: huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+2025-01-09 17:02:41,081 - llm_api - INFO - Loading model from source: huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+2025-01-09 17:02:41,377 - llm_api - ERROR - Failed to initialize generation model huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install 'accelerate>=0.26.0'`
+2025-01-09 17:02:41,377 - api_routes - ERROR - Error initializing model: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install 'accelerate>=0.26.0'`

requirements.txt

@@ -1,22 +1,20 @@
-accelerate==1.1.1
+accelerate==1.2.1
 annotated-types==0.7.0
-anyio==4.6.2.post1
-bitsandbytes==0.45.0
-certifi==2024.8.30
-charset-normalizer==3.4.0
-click==8.1.7
-fastapi==0.115.5
+anyio==4.8.0
+certifi==2024.12.14
+charset-normalizer==3.4.1
+click==8.1.8
+fastapi==0.115.6
 filelock==3.16.1
-fsspec==2024.10.0
+fsspec==2024.12.0
 h11==0.14.0
-huggingface-hub==0.26.3
+huggingface-hub==0.27.1
 idna==3.10
-inquirerpy==0.3.4
-Jinja2==3.1.4
+Jinja2==3.1.5
 MarkupSafe==3.0.2
 mpmath==1.3.0
 networkx==3.4.2
-numpy==2.1.3
+numpy==2.2.1
 nvidia-cublas-cu12==12.4.5.8
 nvidia-cuda-cupti-cu12==12.4.127
 nvidia-cuda-nvrtc-cu12==12.4.127
@@ -30,28 +28,22 @@ nvidia-nccl-cu12==2.21.5
 nvidia-nvjitlink-cu12==12.4.127
 nvidia-nvtx-cu12==12.4.127
 packaging==24.2
-pfzy==0.3.4
-prompt_toolkit==3.0.48
-psutil==6.1.0
-pydantic==2.10.2
-pydantic_core==2.27.1
+psutil==6.1.1
+pydantic==2.10.5
+pydantic_core==2.27.2
 python-dotenv==1.0.1
 PyYAML==6.0.2
 regex==2024.11.6
 requests==2.32.3
-router==0.1
-safetensors==0.4.5
-setuptools==75.6.0
+safetensors==0.5.2
+setuptools==75.8.0
 sniffio==1.3.1
 starlette==0.41.3
 sympy==1.13.1
-tokenizers==0.20.3
+tokenizers==0.21.0
 torch==2.5.1
 tqdm==4.67.1
-transformers==4.46.3
-triton==3.1.0
+transformers==4.47.1
 typing_extensions==4.12.2
-urllib3==2.2.3
-utils==1.0.2
-uvicorn==0.32.1
-wcwidth==0.2.13
+urllib3==2.3.0
+uvicorn==0.34.0