Eeppa commited on
Commit
8ae90bd
·
verified ·
1 Parent(s): 6953393

Delete README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -53
README.md DELETED
@@ -1,53 +0,0 @@
1
- ---
2
- title: Llama 3.2 1B Codex
3
- sdk: gradio
4
- sdk_version: 6.6.0 # Change this from 4.0.0
5
- app_file: app.py
6
- ---
7
-
8
- # 🤖 Llama 3.2 1B Codex
9
-
10
- ## AI Coding Assistant with Thinking Mode
11
-
12
- This Space hosts **Llama-3.2-1B-Codex**, a fine-tuned version of Meta's Llama 3.2 1B Instruct model specialized for code generation with explicit reasoning capabilities.
13
-
14
- ### Features
15
-
16
- - 🧠 **Thinking Mode**: Model shows its reasoning process before writing code
17
- - ⚡ **Fast Mode**: Direct code generation for simple tasks
18
- - 💻 **Multi-language Support**: Python, JavaScript, Java, C++, and more
19
- - 🔍 **Chain-of-Thought**: Alternative reasoning strategy for complex problems
20
- - 🎛️ **Adjustable Parameters**: Control creativity and response length
21
-
22
- ### How to Use
23
-
24
- 1. Type your coding question in the chat box
25
- 2. Enable/disable Thinking Mode based on task complexity
26
- 3. Adjust temperature for creative vs precise responses
27
- 4. Get code with explanations!
28
-
29
- ### Examples
30
-
31
- - "Write a Python function to find the longest common prefix"
32
- - "Implement a binary search tree with insert and search"
33
- - "Create a decorator that measures function execution time"
34
- - "Explain recursion with a practical example"
35
-
36
- ### Built With
37
-
38
- - **Base Model**: Meta Llama 3.2 1B Instruct
39
- - **Fine-tuned on**: Code datasets (The Stack, StarCoderData, CodeFeedback)
40
- - **Framework**: Transformers + PEFT + Gradio
41
-
42
- ### License
43
-
44
- This model is governed by the **Llama 3.2 Community License**.
45
- See [LICENSE.txt](./LICENSE.txt) for full terms.
46
-
47
- ### Attribution
48
-
49
- Built with Llama - Meta's open-source AI model.
50
-
51
- ---
52
-
53
- *Fast, thoughtful code assistance for developers*