munyew commited on
Commit
79e1d99
·
verified ·
1 Parent(s): fd219d4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +38 -6
README.md CHANGED
@@ -1,12 +1,44 @@
1
  ---
2
- title: Mina Test Cloud Minimum
3
- emoji: 💻
4
- colorFrom: gray
5
- colorTo: green
6
  sdk: gradio
7
- sdk_version: 6.13.0
8
  app_file: app.py
9
  pinned: false
 
 
 
 
 
 
 
10
  ---
11
 
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: Virtual Cloud Minimum
3
+ emoji: ☁️
4
+ colorFrom: indigo
5
+ colorTo: blue
6
  sdk: gradio
7
+ sdk_version: 4.44.0
8
  app_file: app.py
9
  pinned: false
10
+ tags:
11
+ - edge-ai
12
+ - mina
13
+ - transformers
14
+ - sea-lion
15
+ - testing
16
+ - cloud
17
  ---
18
 
19
+ # Virtual Cloud Minimum
20
+
21
+ Virtual test environment simulating a **minimum cloud CPU deployment** for transformer-based AI models.
22
+
23
+ ## Constraints
24
+ - **RAM Limit**: 4GB enforced
25
+ - **Format**: HuggingFace Transformers models (NOT GGUF)
26
+ - **Runtime**: Hugging Face `transformers` pipeline
27
+ - **Hardware**: CPU Basic (free tier)
28
+
29
+ ## Use Cases
30
+ - Testing SEA-LION and other transformer-native models
31
+ - Evaluating models before cloud deployment
32
+ - Validating minimum viable cloud configuration
33
+
34
+ ## Test Prompt
35
+ > "Hi Mina, aiyo today so hot sia"
36
+
37
+ ## Recommended Models
38
+ - `aisingapore/sea-lion-7b-instruct` (large, may OOM)
39
+ - `aisingapore/llm-sealion-1b`
40
+ - `microsoft/phi-2` (~5GB, may fail on 4GB limit)
41
+ - Any HuggingFace AutoModelForCausalLM compatible model
42
+
43
+ ## Part of Project Mina
44
+ This space is part of the Mina Edge AI virtual device testing suite.