Update README.md
Browse files
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
|
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
|