Views
No views yet
| Property | Value |
|---|---|
| Model ID | Saugat212/ne-en-nllb-model |
| Base Model | facebook/nllb-200-distilled-600M |
| Architecture | m2m_100 |
| Parameters | 0.6B |
| License | apache-2.0 |
| File | Description |
|---|---|
Fine_Tuning.ipynb | NLLB fine-tuning notebook |
Fine_Tuning_nllb.ipynb | NLLB-specific fine-tuning |
transformer_finetuning.ipynb | Alternative transformer fine-tuning |
data_clean.ipynb | Data cleaning notebook |
Data Fetching from translator.ipynb | Fetching parallel data |
inference.ipynb | Translation inference notebook |
opus-translation.py | OPUS-based translation |
Finetune.md | Quick setup guide |
NLLB_Finetuning_Documentation.md | Detailed NLLB docs |
1from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
2
3model_name = "Saugat212/ne-en-nllb-model"
4tokenizer = AutoTokenizer.from_pretrained(model_name)
5model = AutoModelForSeq2SeqLM.from_pretrained(model_name)1def translate_en_to_ne(text):
2 inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
3 out = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["ne_Latn"], max_new_tokens=128)
4 return tokenizer.decode(out[0], skip_special_tokens=True)
5
6print(translate_en_to_ne("Hello, how are you?"))1def translate_ne_to_en(text):
2 inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)
3 out = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["en_Latn"], max_new_tokens=128)
4 return tokenizer.decode(out[0], skip_special_tokens=True)
5
6print(translate_ne_to_en("नमस्ते, तपाईं कस्तो हुनुहुन्छ?"))English_Sentence and Nepali_Translation columnsFine_Tuning.ipynb or Finetune.md as reference