Translation
Transformers
TensorBoard
Safetensors
PyTorch
Ganda
English
marian
text2text-generation
mlflow
Eval Results (legacy)
Instructions to use openchs/lg-opus-mt-multi-en-synthetic-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openchs/lg-opus-mt-multi-en-synthetic-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="openchs/lg-opus-mt-multi-en-synthetic-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("openchs/lg-opus-mt-multi-en-synthetic-v1") model = AutoModelForSeq2SeqLM.from_pretrained("openchs/lg-opus-mt-multi-en-synthetic-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload training_metrics.json with huggingface_hub
Browse files- training_metrics.json +17 -0
training_metrics.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"training_metrics": {
|
| 3 |
+
"final_bleu": 0.5027952466752211,
|
| 4 |
+
"baseline_bleu": 0.16827042825351704,
|
| 5 |
+
"improvement_percent": 422.77,
|
| 6 |
+
"final_loss": 0.2365337312221527,
|
| 7 |
+
"total_samples": 50012,
|
| 8 |
+
"training_runtime_hours": 6.86,
|
| 9 |
+
"epochs": 8
|
| 10 |
+
},
|
| 11 |
+
"model_info": {
|
| 12 |
+
"base_model": "Helsinki-NLP/opus-mt-mul-en",
|
| 13 |
+
"parameters": "77.5M",
|
| 14 |
+
"language_pair": "lg-en",
|
| 15 |
+
"mlflow_run_id": "212ff762127b4d569dcf850b23f6268b"
|
| 16 |
+
}
|
| 17 |
+
}
|