Agnuxo commited on
Commit
26a1c34
1 Parent(s): 9c76513

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +54 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ model_size: 494034560
3
+ required_memory: 1.84
4
+ accuracy: 0.5080275229357798
5
+ metrics:
6
+ - GLUE_SST-2
7
+ license: apache-2.0
8
+ datasets:
9
+ - jtatman/python-code-dataset-500k
10
+ - Vezora/Tested-143k-Python-Alpaca
11
+ language:
12
+ - en
13
+ - es
14
+ base_model: Qwen/Qwen2-0.5B
15
+ library_name: adapter-transformers
16
+ tags:
17
+ - llama
18
+ - minillama
19
+ - tinyllama
20
+ - tiny
21
+ - mini
22
+ - nemo
23
+ - minitron
24
+ - tinytron
25
+ - ollama
26
+ ---
27
+
28
+ # Uploaded model
29
+
30
+ [<img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" width="100"/><img src="https://github.githubassets.com/assets/GitHub-Logo-ee398b662d42.png" width="100"/>](https://github.com/Agnuxo1)
31
+ - **Developed by:** [Agnuxo](https://github.com/Agnuxo1)
32
+ - **License:** apache-2.0
33
+ - **Finetuned from model:** Agnuxo/Tinytron-Qwen2-0.5B
34
+
35
+ This model was fine-tuned using [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
36
+
37
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
38
+
39
+ ## Benchmark Results
40
+
41
+ This model has been fine-tuned for various tasks and evaluated on the following benchmarks:
42
+
43
+ ### GLUE_SST-2
44
+ **Accuracy:** 0.5080
45
+
46
+ ![GLUE_SST-2 Metrics](./GLUE_SST-2_metrics.png)
47
+
48
+
49
+ Model Size: 494,034,560 parameters
50
+ Required Memory: 1.84 GB
51
+
52
+ For more details, visit my [GitHub](https://github.com/Agnuxo1).
53
+
54
+ Thanks for your interest in this model!