Translation
Transformers
Safetensors
English
Hindi
lstm_seq2seq_en_hi
text2text-generation
se2seq2014
custom_code
Instructions to use kd13/nano-translate-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kd13/nano-translate-v1 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="kd13/nano-translate-v1", trust_remote_code=True)# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("kd13/nano-translate-v1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update modeling_lstm_seq2seq_en_hi.py
Browse files
modeling_lstm_seq2seq_en_hi.py
CHANGED
|
@@ -215,4 +215,6 @@ class Seq2SeqHFModel(PreTrainedModel):
|
|
| 215 |
hidden, cell = past_key_values
|
| 216 |
hidden = hidden.index_select(1, beam_idx)
|
| 217 |
cell = cell.index_select(1, beam_idx)
|
| 218 |
-
return (hidden, cell)
|
|
|
|
|
|
|
|
|
| 215 |
hidden, cell = past_key_values
|
| 216 |
hidden = hidden.index_select(1, beam_idx)
|
| 217 |
cell = cell.index_select(1, beam_idx)
|
| 218 |
+
return (hidden, cell)
|
| 219 |
+
|
| 220 |
+
Seq2SeqHFModel.register_for_auto_class("AutoModelForSeq2SeqLM")
|