ihtesham0345 commited on
Commit
f169fdd
·
1 Parent(s): 99776a0

Switch to Qwen-0.5B (Nano) for instant speed and 100% stability

Browse files
Files changed (2) hide show
  1. PROJECT_DOCS.md +1 -1
  2. services/analyzer.py +2 -2
PROJECT_DOCS.md CHANGED
@@ -20,7 +20,7 @@ We used the following technologies to build this application from scratch:
20
  | Component | Technology | Purpose |
21
  | :--- | :--- | :--- |
22
  | **Framework** | **FastAPI** | High-performance web framework for building the API endpoints. |
23
- | **AI Model** | **Qwen2.5-1.5B-Instruct** | A lightweight 1.5B model running LOCALLY inside the container. 100% Free. |
24
  | **Connection** | **Local Inference (CPU)** | No API calls. The model lives inside your app. Zero external dependencies. |
25
  | **Container** | **Docker + PyTorch** | Includes Torch/Transformers to run the AI engine self-contained. |
26
  | **Deployment** | **Hugging Face Spaces** | The cloud platform hosting the Docker container. |
 
20
  | Component | Technology | Purpose |
21
  | :--- | :--- | :--- |
22
  | **Framework** | **FastAPI** | High-performance web framework for building the API endpoints. |
23
+ | **AI Model** | **Qwen2.5-0.5B-Instruct** | The "Nano" model. Ultra-lightweight (0.5B) for maximum speed and zero timeouts. |
24
  | **Connection** | **Local Inference (CPU)** | No API calls. The model lives inside your app. Zero external dependencies. |
25
  | **Container** | **Docker + PyTorch** | Includes Torch/Transformers to run the AI engine self-contained. |
26
  | **Deployment** | **Hugging Face Spaces** | The cloud platform hosting the Docker container. |
services/analyzer.py CHANGED
@@ -10,8 +10,8 @@ env_path = Path(__file__).resolve().parent.parent.parent / ".env"
10
  load_dotenv(dotenv_path=env_path)
11
 
12
  # Configuration: Run Locally to bypass all API limits/errors
13
- # Qwen2.5-1.5B-Instruct is small enough (3GB RAM) to run on CPU Free Tier
14
- MODEL_ID = "Qwen/Qwen2.5-1.5B-Instruct"
15
 
16
  print(f"⏳ Loading Local Model {MODEL_ID}... (This happens once)")
17
  try:
 
10
  load_dotenv(dotenv_path=env_path)
11
 
12
  # Configuration: Run Locally to bypass all API limits/errors
13
+ # Qwen-0.5B is the "Nano" model - Ultra Fast, designed for Mobile/Limitless CPU use.
14
+ MODEL_ID = "Qwen/Qwen2.5-0.5B-Instruct"
15
 
16
  print(f"⏳ Loading Local Model {MODEL_ID}... (This happens once)")
17
  try: