|
|
--- |
|
|
language: |
|
|
- en |
|
|
- mr |
|
|
- hi |
|
|
- gu |
|
|
- pa |
|
|
- te |
|
|
- ta |
|
|
- ml |
|
|
- kn |
|
|
- sd |
|
|
- ne |
|
|
- ur |
|
|
- as |
|
|
- bn |
|
|
- or |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- gemma |
|
|
- trl |
|
|
base_model: google/gemma-2b |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
<img src="https://github.com/Pmking27/AutoTalker/assets/97112558/96853321-e460-4464-a062-9bd1633964d8" width="600" height="600"> |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** pmking27 |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** google/gemma-2b |
|
|
|
|
|
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
### Running Model: |
|
|
|
|
|
```python |
|
|
# Importing necessary modules |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
# Setting the device to load the model onto (assuming GPU availability) |
|
|
device = 'cuda' |
|
|
|
|
|
# Loading the tokenizer for the model |
|
|
tokenizer = AutoTokenizer.from_pretrained("pmking27/PrathameshLLM-2B") |
|
|
|
|
|
# Loading the pre-trained model |
|
|
model = AutoModelForCausalLM.from_pretrained("pmking27/PrathameshLLM-2B") |
|
|
|
|
|
# Defining the Alpaca prompt template |
|
|
alpaca_prompt = """ |
|
|
### Instruction: |
|
|
{} |
|
|
|
|
|
### Input: |
|
|
{} |
|
|
|
|
|
### Response: |
|
|
{}""" |
|
|
|
|
|
# Providing the input to the model |
|
|
model_inputs = tokenizer( |
|
|
[ |
|
|
alpaca_prompt.format( |
|
|
''' |
|
|
You're an assistant trained to answer questions using the given context. |
|
|
|
|
|
context: |
|
|
|
|
|
General elections will be held in India from 19 April 2024 to 1 June 2024 to elect the 543 members of the 18th Lok Sabha. The elections will be held in seven phases and the results will be announced on 4 June 2024. This will be the largest-ever election in the world, surpassing the 2019 Indian general election, and will be the longest-held general elections in India with a total span of 44 days (excluding the first 1951–52 Indian general election). The incumbent prime minister Narendra Modi who completed a second term will be contesting elections for a third consecutive term. |
|
|
|
|
|
Approximately 960 million individuals out of a population of 1.4 billion are eligible to participate in the elections, which are expected to span a month for completion. The Legislative assembly elections in the states of Andhra Pradesh, Arunachal Pradesh, Odisha, and Sikkim will be held simultaneously with the general election, along with the by-elections for 35 seats among 16 states. |
|
|
''', # instruction |
|
|
"भारतातील सार्वत्रिक निवडणुका किती टप्प्यात पार पडतील?", # input |
|
|
"", # output - leave this blank for generation! |
|
|
) |
|
|
], return_tensors = "pt") |
|
|
|
|
|
# Moving model inputs to the specified device |
|
|
model_inputs.to(device) |
|
|
model.to(device) |
|
|
|
|
|
# Generating responses from the model |
|
|
outputs = model.generate(**model_inputs, max_new_tokens=100) |
|
|
decoded_output = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0] |
|
|
|
|
|
# Finding the start and end positions of the response |
|
|
start_marker = "### Response:" |
|
|
end_marker = "<eos>" |
|
|
start_pos = decoded_output.find(start_marker) + len(start_marker) |
|
|
end_pos = decoded_output.find(end_marker, start_pos) |
|
|
|
|
|
# Extracting the response text |
|
|
response_text = decoded_output[start_pos:end_pos].strip() |
|
|
|
|
|
print(response_text) |
|
|
|
|
|
``` |
|
|
|
|
|
### Output: |
|
|
|
|
|
```markdown |
|
|
भारतातील सार्वत्रिक निवडणुका 7 टप्प्यांमध्ये पार पडतील. |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
