DrChamyoung commited on
Commit
112bc7c
1 Parent(s): fae4688

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -3
README.md CHANGED
@@ -1,3 +1,49 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - inbora studio
5
+ - drchamyoung
6
+ - Neural Network
7
+ - DLL
8
+ - Deep ONNX
9
+ - Behaviour Agents
10
+ ---
11
+ # Xieral Code Gen 3B
12
+
13
+ Xieral Code Gen 3B is a decoder-only language model with 2.7 billion parameters. Developed from the `Xieral-Code-Gen-3b`, this model is designed specifically for code generation and software engineering tasks.
14
+
15
+ ## Model Overview
16
+
17
+ - **Architecture**: Decoder-only language model
18
+ - **Parameters**: 2.7 billion
19
+ - **Training Data**: Combination of publicly available and synthetic datasets
20
+ - **Optimization**: Direct Preference Optimization (DPO)
21
+ - **Fine-tuning**: General code/software engineering conversations, SQL query generation, and discussion
22
+
23
+ ## Performance
24
+
25
+ Xieral Code Gen 3B has demonstrated competitive performance compared to other models of similar size:
26
+
27
+ - **MultiPL-E Metrics**: Evaluated across various programming languages using the BigCode Evaluation Harness.
28
+ - **MT Bench**: Shows strong results on code-related tasks.
29
+
30
+ ## Usage
31
+
32
+ This model is well-suited for:
33
+
34
+ - General code/software engineering conversations
35
+ - SQL query generation and discussion
36
+
37
+ ### Requirements
38
+
39
+ To run Xieral Code Gen 3B locally, you will need:
40
+
41
+ - **VRAM**: 8GB+ (Graphics card with sufficient VRAM)
42
+ - **Dependencies**: Ensure you have the necessary libraries and environment set up to run the model.
43
+
44
+ ## Installation
45
+
46
+ To install the required dependencies, use:
47
+
48
+ ```bash
49
+ pip install -r requirements.txt