ihtesham0345 commited on
Commit
ad41aff
·
1 Parent(s): d877e39

Switch to Zephyr-7B-Beta for Chat API compatibility

Browse files
Files changed (2) hide show
  1. PROJECT_DOCS.md +1 -1
  2. services/analyzer.py +1 -1
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** | **Mistral-7B-Instruct-v0.3** | A high-intelligence 7 Billion parameter model accessed via API. |
24
  | **Connection** | **HF Inference Client** | Connects to Hugging Face's serverless GPU cluster. |
25
  | **Container** | **Docker** | Lightweight container (no heavy ML libraries needed anymore). |
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** | **Zephyr-7B-Beta** | A high-intelligence 7 Billion parameter model (Mistral fine-tune). |
24
  | **Connection** | **HF Inference Client** | Connects to Hugging Face's serverless GPU cluster. |
25
  | **Container** | **Docker** | Lightweight container (no heavy ML libraries needed anymore). |
26
  | **Deployment** | **Hugging Face Spaces** | The cloud platform hosting the Docker container. |
services/analyzer.py CHANGED
@@ -10,7 +10,7 @@ load_dotenv(dotenv_path=env_path)
10
 
11
  # Configuration: Use a powerful model available via free Serverless API
12
  # Mistral-7B-Instruct-v0.3 is excellent for following JSON instructions.
13
- MODEL_ID = "mistralai/Mistral-7B-Instruct-v0.3"
14
 
15
  # Initialize Client
16
  # It automatically picks up HF_TOKEN from environment if set, otherwise works anonymously (with lower limits)
 
10
 
11
  # Configuration: Use a powerful model available via free Serverless API
12
  # Mistral-7B-Instruct-v0.3 is excellent for following JSON instructions.
13
+ MODEL_ID = "HuggingFaceH4/zephyr-7b-beta"
14
 
15
  # Initialize Client
16
  # It automatically picks up HF_TOKEN from environment if set, otherwise works anonymously (with lower limits)