Commit
•
671254b
1
Parent(s):
34faf87
Update README.md (#2)
Browse files- Update README.md (786be0cf6a09d8449eb0c05554e40672ea9eedb1)
Co-authored-by: Pakawat Phasook <SuperkingbasSKB@users.noreply.huggingface.co>
README.md
CHANGED
@@ -36,7 +36,7 @@ KeyError: 'qwen2'
|
|
36 |
```
|
37 |
## **Support Community**
|
38 |
|
39 |
-
**https://discord.gg/
|
40 |
|
41 |
## **Implementation**
|
42 |
|
@@ -55,7 +55,7 @@ tokenizer = AutoTokenizer.from_pretrained("nectec/OpenThaiLLM-DoodNiLT-V1.0.0-Be
|
|
55 |
|
56 |
prompt = "บริษัท A มีต้นทุนคงที่ 100,000 บาท และต้นทุนผันแปรต่อหน่วย 50 บาท ขายสินค้าได้ในราคา 150 บาทต่อหน่วย ต้องขายสินค้าอย่างน้อยกี่หน่วยเพื่อให้ถึงจุดคุ้มทุน?"
|
57 |
messages = [
|
58 |
-
{"role": "system", "content": "
|
59 |
{"role": "user", "content": prompt}
|
60 |
]
|
61 |
text = tokenizer.apply_chat_template(
|
@@ -68,20 +68,21 @@ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|
68 |
generated_ids = model.generate(
|
69 |
model_inputs.input_ids,
|
70 |
max_new_tokens=4096,
|
71 |
-
repetition_penalty=1.
|
|
|
72 |
)
|
73 |
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
74 |
print(response)
|
75 |
```
|
76 |
|
77 |
## **Evaluation Performance**
|
78 |
-
| Model |
|
79 |
-
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
|
|
84 |
-
| Meta-Llama-3.1-8B |
|
85 |
|
86 |
|
87 |
## **Citation**
|
|
|
36 |
```
|
37 |
## **Support Community**
|
38 |
|
39 |
+
**https://discord.gg/3WJwJjZt7r**
|
40 |
|
41 |
## **Implementation**
|
42 |
|
|
|
55 |
|
56 |
prompt = "บริษัท A มีต้นทุนคงที่ 100,000 บาท และต้นทุนผันแปรต่อหน่วย 50 บาท ขายสินค้าได้ในราคา 150 บาทต่อหน่วย ต้องขายสินค้าอย่างน้อยกี่หน่วยเพื่อให้ถึงจุดคุ้มทุน?"
|
57 |
messages = [
|
58 |
+
{"role": "system", "content": "You are Pathumma LLM, created by NECTEC. Your are a helpful assistant."},
|
59 |
{"role": "user", "content": prompt}
|
60 |
]
|
61 |
text = tokenizer.apply_chat_template(
|
|
|
68 |
generated_ids = model.generate(
|
69 |
model_inputs.input_ids,
|
70 |
max_new_tokens=4096,
|
71 |
+
repetition_penalty=1.1,
|
72 |
+
temperature = 0.4
|
73 |
)
|
74 |
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
75 |
print(response)
|
76 |
```
|
77 |
|
78 |
## **Evaluation Performance**
|
79 |
+
| Model | m3exam | thaiexam | xcopa | belebele | xnli | thaisentiment | XL sum | flores200 eng > th | flores200 th > eng | iapp | AVG(NLU) | AVG(MC) | AVG(NLG)
|
80 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
81 |
+
| Pathumma-llm-text-1.0.0 | 55.02 | 51.32 | 83 | 77.77 | 40.11 | 41.29 | 16.9286253 | 26.54 | 51.88 | 41.28 |
|
82 |
+
| Openthaigpt1.5-7b-instruct | 54.01 | 52.04 | 85.4 | 79.44 | 39.7 | 50.24 | 18.11 | 29.09 | 29.58 | 32.49 | 63.70 | 53.03 | 27.32 |
|
83 |
+
| SeaLLMs-v3-7B-Chat | 51.43 | 51.33 | 83.4 | 78.22 | 34.05 | 39.57 | 20.27 | 32.91 | 28.8 | 48.12 | 58.81 | 51.38 | 32.53 |
|
84 |
+
| llama-3-typhoon-v1.5-8B | 43.82 | 41.95 | 81.6 | 71.89 | 33.35 | 38.45 | 16.66 | 31.94 | 28.86 | 54.78 | 56.32 | 42.89 | 33.06 |
|
85 |
+
| Meta-Llama-3.1-8B-Instruct | 45.11 | 43.89 | 73.4 | 74.89 | 33.49 | 45.45 | 21.61 | 30.45 | 32.28 | 68.57 | 56.81 | 44.50 | 38.23 |
|
86 |
|
87 |
|
88 |
## **Citation**
|