kobkrit commited on
Commit
2bf0d3a
1 Parent(s): 83dca2e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -24,7 +24,7 @@ tags:
24
  - Built upon a foundation of **more than 65 billion Thai language words** and meticulously fine-tuned with over 1 million Thai instruction examples.
25
  - Capable of understanding and processing **input contexts of up to 4096 Thai words**, allowing for detailed and complex instructions.
26
 
27
- ## Benchmark by Multiple Choices Thai Exams
28
  ** Please take a look at ``OTG 7b (March 2024)`` for this model's evaluation result.
29
 
30
  | **Exams** | **OTG 7b (Aug 2023)** | **OTG 13b (Dec 2023)** | **OTG 7b (March 2024)** | **OTG 13b (March 2024)** | **OTG 70b (March 2024)** | **SeaLLM 7b v1** | **SeaLLM 7b v2** | **SeaLion 7b** | **WanchanGLM 7b** | **Sailor-7b-Chat** | **TyphoonGPT 7b Instruct** | **GPT3.5** | **GPT4** | **Gemini Pro** | **Gemini 1.5** | **Claude 3 Haiku** | **Claude 3 Sonnet** | **Claude 3 Opus** |
@@ -42,6 +42,7 @@ tags:
42
 
43
 
44
  ### Benchmark Configuration
 
45
  - Multiple Choice (1)-(5)
46
  - Zero shot only
47
  - Tested on Unseen test set only
 
24
  - Built upon a foundation of **more than 65 billion Thai language words** and meticulously fine-tuned with over 1 million Thai instruction examples.
25
  - Capable of understanding and processing **input contexts of up to 4096 Thai words**, allowing for detailed and complex instructions.
26
 
27
+ ## Benchmark by OpenThaiGPT Eval
28
  ** Please take a look at ``OTG 7b (March 2024)`` for this model's evaluation result.
29
 
30
  | **Exams** | **OTG 7b (Aug 2023)** | **OTG 13b (Dec 2023)** | **OTG 7b (March 2024)** | **OTG 13b (March 2024)** | **OTG 70b (March 2024)** | **SeaLLM 7b v1** | **SeaLLM 7b v2** | **SeaLion 7b** | **WanchanGLM 7b** | **Sailor-7b-Chat** | **TyphoonGPT 7b Instruct** | **GPT3.5** | **GPT4** | **Gemini Pro** | **Gemini 1.5** | **Claude 3 Haiku** | **Claude 3 Sonnet** | **Claude 3 Opus** |
 
42
 
43
 
44
  ### Benchmark Configuration
45
+ - Benchmark source code and Exams: https://github.com/OpenThaiGPT/openthaigpt_eval
46
  - Multiple Choice (1)-(5)
47
  - Zero shot only
48
  - Tested on Unseen test set only