Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,6 @@ language:
|
|
| 28 |
| base-model-7b | ARC-easy-dev | 2 | en-1 | 0.41929 |
|
| 29 |
| base-model-7b | ARC-easy-dev | 80 | en-2 | 0.39122 |
|
| 30 |
| base-model-7b | ARC-easy-dev | 300 | en-1 | 0.34448 |
|
| 31 |
-
|
| 32 |
| model | dataset | max_token | prompt | score |
|
| 33 |
|---------------|------------------|-----------|--------|---------|
|
| 34 |
| fa-model-7b | ARC-easy-dev | 80 | en-1 | 0.37894 |
|
|
@@ -37,13 +36,16 @@ language:
|
|
| 37 |
| fa-model-7b | ARC-easy-dev | 300 | fa-1 | 0.25752 |
|
| 38 |
| fa-model-7b | ARC-easy-dev | 2 | fa-1 | 0.24035 |
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
| model | dataset | max_token | prompt | score |
|
| 41 |
|---------------|--------------------|-----------|--------|---------|
|
| 42 |
| base-model-7b | ARC-challenge-dev | 80 | en-2 | 0.37123 |
|
| 43 |
| base-model-7b | ARC-challenge-dev | 2 | en-2 | 0.36789 |
|
| 44 |
| base-model-7b | ARC-challenge-dev | 2 | en-1 | 0.35451 |
|
| 45 |
| base-model-7b | ARC-challenge-dev | 80 | en-1 | 0.33779 |
|
| 46 |
-
|
| 47 |
| model | dataset | max_token | prompt | score |
|
| 48 |
|---------------|--------------------|-----------|--------|---------|
|
| 49 |
| fa-model-7b | ARC-challenge-dev | 2 | en-1 | 0.39298 |
|
|
@@ -56,15 +58,12 @@ language:
|
|
| 56 |
|
| 57 |
```python
|
| 58 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 59 |
-
|
| 60 |
tokenizer = AutoTokenizer.from_pretrained("aidal/Persian-Mistral-7B")
|
| 61 |
model = AutoModelForCausalLM.from_pretrained("aidal/Persian-Mistral-7B")
|
| 62 |
-
|
| 63 |
input_text = "پایتخت ایران کجاست؟"
|
| 64 |
input_ids = tokenizer(input_text, return_tensors="pt")
|
| 65 |
-
|
| 66 |
outputs = model.generate(**input_ids)
|
| 67 |
print(tokenizer.decode(outputs[0]))
|
| 68 |
```
|
| 69 |
----
|
| 70 |
-
# Training and finetuning
|
|
|
|
| 28 |
| base-model-7b | ARC-easy-dev | 2 | en-1 | 0.41929 |
|
| 29 |
| base-model-7b | ARC-easy-dev | 80 | en-2 | 0.39122 |
|
| 30 |
| base-model-7b | ARC-easy-dev | 300 | en-1 | 0.34448 |
|
|
|
|
| 31 |
| model | dataset | max_token | prompt | score |
|
| 32 |
|---------------|------------------|-----------|--------|---------|
|
| 33 |
| fa-model-7b | ARC-easy-dev | 80 | en-1 | 0.37894 |
|
|
|
|
| 36 |
| fa-model-7b | ARC-easy-dev | 300 | fa-1 | 0.25752 |
|
| 37 |
| fa-model-7b | ARC-easy-dev | 2 | fa-1 | 0.24035 |
|
| 38 |
|
| 39 |
+
<br>
|
| 40 |
+
<br>
|
| 41 |
+
<br>
|
| 42 |
+
|
| 43 |
| model | dataset | max_token | prompt | score |
|
| 44 |
|---------------|--------------------|-----------|--------|---------|
|
| 45 |
| base-model-7b | ARC-challenge-dev | 80 | en-2 | 0.37123 |
|
| 46 |
| base-model-7b | ARC-challenge-dev | 2 | en-2 | 0.36789 |
|
| 47 |
| base-model-7b | ARC-challenge-dev | 2 | en-1 | 0.35451 |
|
| 48 |
| base-model-7b | ARC-challenge-dev | 80 | en-1 | 0.33779 |
|
|
|
|
| 49 |
| model | dataset | max_token | prompt | score |
|
| 50 |
|---------------|--------------------|-----------|--------|---------|
|
| 51 |
| fa-model-7b | ARC-challenge-dev | 2 | en-1 | 0.39298 |
|
|
|
|
| 58 |
|
| 59 |
```python
|
| 60 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
| 61 |
tokenizer = AutoTokenizer.from_pretrained("aidal/Persian-Mistral-7B")
|
| 62 |
model = AutoModelForCausalLM.from_pretrained("aidal/Persian-Mistral-7B")
|
|
|
|
| 63 |
input_text = "پایتخت ایران کجاست؟"
|
| 64 |
input_ids = tokenizer(input_text, return_tensors="pt")
|
|
|
|
| 65 |
outputs = model.generate(**input_ids)
|
| 66 |
print(tokenizer.decode(outputs[0]))
|
| 67 |
```
|
| 68 |
----
|
| 69 |
+
# Training and finetuning
|