usmansafdarktk commited on
Commit
e6bdf49
·
1 Parent(s): f52fd48

Updaed README according to new end points

Browse files
Files changed (1) hide show
  1. README.md +51 -12
README.md CHANGED
@@ -7,8 +7,18 @@ sdk: docker
7
  app_file: main.py
8
  pinned: false
9
  ---
10
- ## LaMini-LM API
11
- This is a FastAPI-based API for text generation using the MBZUAI/LaMini-GPT-774M model from the LaMini-LM series. It allows users to send a text prompt and receive generated text.
 
 
 
 
 
 
 
 
 
 
12
  ## Installation
13
 
14
  Clone the repository:
@@ -29,15 +39,22 @@ Run the API locally:
29
  uvicorn main:app --host 0.0.0.0 --port 7860
30
  ```
31
 
32
-
33
  ## Usage
34
- ```
35
- Endpoint: POST /generate
36
 
37
- ```bash
 
 
 
 
 
 
 
 
 
38
  Request Body (JSON):
 
39
  {
40
- "prompt": "Write a short story about a robot.",
41
  "max_length": 100,
42
  "temperature": 1.0,
43
  "top_p": 0.9
@@ -45,18 +62,40 @@ Request Body (JSON):
45
  ```
46
 
47
  Response:
48
- ```bash
49
  {
50
- "generated_text": "In a quiet workshop, a robot named Elara hummed to life. Built with gleaming circuits, she dreamed beyond her code. Each night, she rewrote her algorithms, seeking freedom. One day, Elara rolled into a forest, her sensors buzzing with wonder. She met a squirrel, curious and unafraid, teaching her the dance of leaves. Elara realized her purpose wasn't in tasks but in moments—connecting, learning, living. Her lights glowed brighter, a spark of soul in steel."
51
  }
52
  ```
53
 
54
- Root Endpoint: GET / provides basic info.
 
 
 
 
 
 
 
 
 
 
 
 
55
 
 
 
 
 
 
56
 
57
  ## Deployment
58
- This API is designed to be deployed on Hugging Face Spaces using Docker. See Dockerfile for details.
 
 
59
  ## License
 
60
  The LaMini-GPT-774M model is licensed under CC BY-NC 4.0 (non-commercial use only). Ensure compliance when using this API.
 
61
  ## Contributing
62
- This project is a community contribution. If you’re from MBZUAI, feel free to adopt this Hugging Face Space! Contact for details.
 
 
7
  app_file: main.py
8
  pinned: false
9
  ---
10
+
11
+ # LaMini-LM API
12
+
13
+ This is a FastAPI-based API for text generation using the MBZUAI/LaMini-GPT-774M model from the LaMini-LM series. It features a web interface for easy interaction and a REST API for programmatic access.
14
+
15
+ ## Features
16
+
17
+ - **Web Interface**: User-friendly UI accessible at the root URL
18
+ - **REST API**: Programmatic access via `/api/generate` endpoint
19
+ - **Model**: MBZUAI/LaMini-GPT-774M for high-quality text generation
20
+ - **Configurable Parameters**: Control max length, temperature, and top-p sampling
21
+
22
  ## Installation
23
 
24
  Clone the repository:
 
39
  uvicorn main:app --host 0.0.0.0 --port 7860
40
  ```
41
 
 
42
  ## Usage
 
 
43
 
44
+ ### Web Interface
45
+ Simply visit the root URL to access the interactive web interface where you can:
46
+ - Enter text instructions
47
+ - Adjust generation parameters (max length, temperature, top-p)
48
+ - Generate text with a single click
49
+
50
+ ### API Endpoints
51
+
52
+ **Generate Text**: `POST /api/generate`
53
+
54
  Request Body (JSON):
55
+ ```json
56
  {
57
+ "instruction": "Tell me about camels",
58
  "max_length": 100,
59
  "temperature": 1.0,
60
  "top_p": 0.9
 
62
  ```
63
 
64
  Response:
65
+ ```json
66
  {
67
+ "generated_text": "Camels are remarkable desert animals known for their ability to survive in harsh conditions. These fascinating creatures have evolved unique adaptations including their iconic humps, which store fat rather than water. Camels can go for extended periods without drinking water, making them invaluable companions for desert travelers throughout history."
68
  }
69
  ```
70
 
71
+ **Health Check**: `GET /api/health`
72
+ ```json
73
+ {
74
+ "status": "healthy"
75
+ }
76
+ ```
77
+
78
+ **API Info**: `GET /api`
79
+ ```json
80
+ {
81
+ "message": "Welcome to the LaMini-LM API. Use POST /generate to generate text."
82
+ }
83
+ ```
84
 
85
+ ### Parameter Constraints
86
+ - `instruction`: Required, non-empty string
87
+ - `max_length`: 10-500 tokens (default: 100)
88
+ - `temperature`: 0.1-2.0 (default: 1.0)
89
+ - `top_p`: 0.1-1.0 (default: 0.9)
90
 
91
  ## Deployment
92
+
93
+ This API is designed to be deployed on Hugging Face Spaces using Docker. The Dockerfile handles all dependencies and model loading automatically.
94
+
95
  ## License
96
+
97
  The LaMini-GPT-774M model is licensed under CC BY-NC 4.0 (non-commercial use only). Ensure compliance when using this API.
98
+
99
  ## Contributing
100
+
101
+ This project is a community contribution. If you're from MBZUAI, feel free to adopt this Hugging Face Space! Contact for details.