Translation
Transformers
Safetensors
English
Hindi
lstm_seq2seq_bahdanau_en_hi
text2text-generation
en-hi
custom_code
Instructions to use kd13/nano-translate-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kd13/nano-translate-v2 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-v2", trust_remote_code=True)# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("kd13/nano-translate-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update generation_config.json
Browse files- generation_config.json +7 -6
generation_config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 2,
|
| 3 |
"decoder_start_token_id": 2,
|
| 4 |
-
"early_stopping": true,
|
| 5 |
"eos_token_id": 3,
|
| 6 |
-
"
|
| 7 |
-
"max_length": 100,
|
| 8 |
"num_beams": 10,
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"decoder_start_token_id": 2,
|
|
|
|
| 5 |
"eos_token_id": 3,
|
| 6 |
+
"pad_token_id": 0,
|
|
|
|
| 7 |
"num_beams": 10,
|
| 8 |
+
"do_sample": false,
|
| 9 |
+
"early_stopping": true,
|
| 10 |
+
"length_penalty": 0.9,
|
| 11 |
+
"max_length": 42
|
| 12 |
+
}
|