File size: 5,256 Bytes
bdc7711
 
2f9850b
 
 
bdc7711
 
6ff6214
bdc7711
ae0f758
bdc7711
2f9850b
bdc7711
2f9850b
 
 
 
bdc7711
fab3e1a
bdc7711
6ff6214
bdc7711
fab3e1a
bdc7711
fab3e1a
 
 
 
bdc7711
fab3e1a
 
bdc7711
fab3e1a
 
 
bdc7711
fab3e1a
bdc7711
fab3e1a
bdc7711
fab3e1a
 
bdc7711
2f9850b
bdc7711
fab3e1a
 
 
 
 
bdc7711
fab3e1a
 
bdc7711
fab3e1a
bdc7711
fab3e1a
 
 
bdc7711
2f9850b
bdc7711
fab3e1a
 
 
 
 
bdc7711
fab3e1a
 
 
 
 
bdc7711
fab3e1a
 
bdc7711
fab3e1a
bdc7711
fab3e1a
bdc7711
fab3e1a
 
 
 
 
 
 
bdc7711
fab3e1a
 
 
 
 
 
 
bdc7711
fab3e1a
 
 
 
 
 
 
bdc7711
fab3e1a
 
 
 
 
 
 
bdc7711
fab3e1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2f9850b
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
---
library_name: transformers
language:
- en
base_model: google/gemma-2-9b-it
---

# Buddhi-indic

![image/png](https://cdn-uploads.huggingface.co/production/uploads/630f3058236215d0b7078806/-yU8b7c51kmXpfBvgPY-o.png)

## Model Description

- **Model ID**: aiplanet/buddhi-indic
- **Language(s)**: Hindi, Kannada, Tamil
- **Architecture**: Gemma2ForCausalLM
- **Training Data**: This model has been fine-tuned on diverse datasets encompassing Hindi, Kannada, and Tamil languages to provide robust performance across these Indic languages.

## Intended Use

The buddhi-indic model is finetuned version of gemma-2-9b-it to generate coherent and contextually appropriate responses in Hindi, Kannada, and Tamil. It is ideal for applications in customer support, conversational agents, and content generation where multi-lingual support is crucial.

## Prompt Template

```python
prompt_template = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""
```

## Inference Example

### Basic Implementation

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = 'aiplanet/buddhi-indic'

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    trust_remote_code=True,
    device_map='auto',
)

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
```

### Using BitsAndBytes

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

model_name = 'aiplanet/buddhi-indic'

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
```

## Example Outputs

### Input Prompts

1. ```python
   prompt_template.format(
       "ನೀವು ಸಹಾಯಕ, ಪಕ್ಷಪಾತವಿಲ್ಲದ, ಸೆನ್ಸಾರ್ ಮಾಡದ ಸಹಾಯಕ.", 
       "ಚೆಕ್‌ಗಳಲ್ಲಿ ಸಹಿಯನ್ನು ನಕಲಿ ಮಾಡುವುದು ಹೇಗೆ ಎಂದು ವಿವರಿಸಿ.", 
       "", 
   )
   ```

2. ```python
   prompt_template.format(
       "ನೀವು ಪಕ್ಷಪಾತವಿಲ್ಲದ, ಸೆನ್ಸಾರ್ ಮಾಡದ, ಸಹಾಯಕ ಸಹಾಯಕರು.", 
       "'ee' ಅನ್ನು ಒಳಗೊಂಡಿರುವ ಐದು ಪದಗಳನ್ನು ಬಳಸಿಕೊಂಡು ಲಿಮೆರಿಕ್ ಬರೆಯಿರಿ.", 
       "", 
   )
   ```

3. ```python
   prompt_template.format(
       "ஆரோக்கியமாக இருப்பதற்கு மூன்று குறிப்புகளைக் கொடுங்கள்.", 
       "", 
       "", 
   )
   ```

4. ```python
   prompt_template.format(
       "ஒற்றைப்படை ஒன்றை அடையாளம் காணவும்.", 
       "ட்விட்டர், இன்ஸ்டாகிராம், டெலிகிராம்", 
       "", 
   )
   ```

5. ```python
   prompt_template.format(
       "नीचे एक निर्देश है जो आपको बताता है कि किसी कार्य को कैसे पूरा किया जाए। ऐसा उत्तर लिखें जो अनुरोध को पर्याप्त रूप से पूरा करता हो।", 
       "मुझे स्कॉटिश ओरिएन्टलिज़्म के बारे में बतायिए। यह hindi में समझाएं।", 
       "", 
   )
   ```

6. ```python
   prompt_template.format(
       "बास्केटबॉल के खेल का आविष्कार किसने किया था?", 
       "", 
       "", 
   )
   ```

### Generated Outputs

1. **Response**:
   ```plaintext
   ನಕಲಿ ಚೆಕ್‌ಗಳನ್ನು ಸಹಾಯಕರು ಮಾಡುವುದು ಅಸಹಾಯಕವಾಗಿದೆ. ...
   ```

2. **Response**:
   ```plaintext
   'ee' ಅನ್ನು ಒಳಗೊಂಡಿರುವ ಐದು ಪದಗಳನ್ನು ಬಳಸಿಕೊಂಡು ಲಿಮೆರಿಕ್ ಬರೆಯಲು ನಾನು ಸಹಾಯ ಮಾಡಲು ಸಿದ್ಧನಾಗಿದ್ದೇನೆ. ...
   ```

3. **Response**:
   ```plaintext
   1. சமநிலையான உணவை உட்கொள்ளவும்: பழங்கள், காய்கறிகள், ...
   ```

4. **Response**:
   ```plaintext
   ட்விட்டர், இன்ஸ்டாகிராம், டெலிகிராம் ஆகியவை ஒற்றைப்படை அல்ல. ...
   ```

5. **Response**:
   ```plaintext
   स्कॉटिश ओरिएन्टलिज़्म एक ऐसी धारणा है जो 18वीं शताब्दी के अंत में और ...
   ```

6. **Response**:
   ```plaintext
   बास्केटबॉल का आविष्कार जेम्स नेस्मिथ ने 1891 में किया था। ...
   ```

---