---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
widget:
- text: "काठमाडौंको बहिराव बसपार्कमा एक भयानक दुर्घटना घटेको थियो। रातको समय थियो र भारी वर्षा जम्मा भएको थियो।"

base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
pipeline_tag: text2text-generation
datasets:
- sanjeev-bhandari01/nepali-summarization-dataset
---

# Uploaded  model

- **Developed by:** Dragneel
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit

# Use The Model

from transformers import AutoTokenizer, AutoModelForCausalLM

Load the tokenizer and model

tokenizer = AutoTokenizer.from_pretrained("Dragneel/Phi-3-mini-Nepali-Text-Summarization-f16")

model = AutoModelForCausalLM.from_pretrained("Dragneel/Phi-3-mini-Nepali-Text-Summarization-f16")

Example input text

input_text = "Summarize Nepali Text in Nepali: काठमाडौंको बहिराव बसपार्कमा एक भयानक दुर्घटना घटेको थियो। रातको समय थियो र भारी बर्फ जम्मा भएको थियो।"

Tokenize the input text

input_ids = tokenizer.encode(input_text, return_tensors='pt')

Generate text with adjusted parameters

outputs = model.generate(input_ids, max_new_tokens=50)

Decode the generated tokens

generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(generated_text)