Update README.md
Browse files
README.md
CHANGED
@@ -124,14 +124,21 @@ The accelerated partition is composed of 1,120 nodes with the following specific
|
|
124 |
---
|
125 |
|
126 |
## How to use
|
127 |
-
This section offers examples of how to perform inference using various methods.
|
128 |
|
129 |
-
|
130 |
|
131 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
|
133 |
-
|
134 |
-
|
|
|
|
|
135 |
|
136 |
```python
|
137 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
@@ -154,7 +161,6 @@ input_length = input_ids.shape[1]
|
|
154 |
generated_text = tokenizer.decode(output_ids[0, input_length: ], skip_special_tokens=True).strip()
|
155 |
# Ahir se'n va anar, va agafar les seves coses i es va posar a navegar.
|
156 |
```
|
157 |
-
</details>
|
158 |
|
159 |
<br>
|
160 |
|
@@ -204,11 +210,14 @@ for i, output in enumerate(outputs):
|
|
204 |
|
205 |
print("Generated Translations:", results_detokenized)
|
206 |
|
207 |
-
#Generated Translations: ["Ahir se'n va anar, va agafar les seves coses i es va posar a navegar.",
|
208 |
-
|
|
|
|
|
209 |
```
|
210 |
</details>
|
211 |
|
|
|
212 |
## Data
|
213 |
|
214 |
|
|
|
124 |
---
|
125 |
|
126 |
## How to use
|
|
|
127 |
|
128 |
+
To translate with the salamandraTA-2b model, first you need to create a prompt that specifies the source and target languages in this format:
|
129 |
|
130 |
+
```css
|
131 |
+
[source_language] sentence \n[target_language]
|
132 |
+
```
|
133 |
+
|
134 |
+
You can translate between these languages by using their names directly:
|
135 |
+
|
136 |
+
Italian, Portuguese, German, English, Spanish, Euskera, Galician, French, Bulgarian, Czech, Lithuanian, Croatian, Dutch, Romanian, Danish, Greek, Finnish, Hungarian, Slovak, Slovenian, Estonian, Polish, Latvian, Swedish, Maltese, Irish, Aranese, Aragonese, Asturian.
|
137 |
|
138 |
+
|
139 |
+
### Inference
|
140 |
+
|
141 |
+
To translate from Spanish to Catalan using Huggingface's AutoModel class on a single sentence you can use the following code:
|
142 |
|
143 |
```python
|
144 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
161 |
generated_text = tokenizer.decode(output_ids[0, input_length: ], skip_special_tokens=True).strip()
|
162 |
# Ahir se'n va anar, va agafar les seves coses i es va posar a navegar.
|
163 |
```
|
|
|
164 |
|
165 |
<br>
|
166 |
|
|
|
210 |
|
211 |
print("Generated Translations:", results_detokenized)
|
212 |
|
213 |
+
#Generated Translations: ["Ahir se'n va anar, va agafar les seves coses i es va posar a navegar.",
|
214 |
+
#"Es va acomiadar i va decidir batre's en duel amb el mar, i rec贸rrer el m贸n en el seu veler",
|
215 |
+
#"El seu cor va buscar una forma diferent de viure, per貌 les onades li van cridar: V茅s amb els altres",
|
216 |
+
#"I es va adormir i la nit li va cridar: On vas, i en els seus somnis va dibuixar gavines, i va pensar: Avui he de tornar."]
|
217 |
```
|
218 |
</details>
|
219 |
|
220 |
+
|
221 |
## Data
|
222 |
|
223 |
|