Update README.md

README.md

@@ -102,36 +102,54 @@ language:
 - zh
 - zu
 license: mit
+tags:
+- ctranslate2
 ---
 
 Converted 5/13/23 to Ctranslate2
 ```bash
 export ORG="facebook"
-export NAME="m2m100_1.2B"
+export NAME="m2m100_PARAMS"
 ct2-transformers-converter --model "$ORG/$NAME" --copy_files .gitattributes README.md generation_config.json sentencepiece.bpe.model  special_tokens_map.json tokenizer_config.json vocab.json --quantization float16
 ```
 Fast-Inference with Ctranslate2
 Speedup inference by 2x-8x using int8 inference in C++
-
 quantized version of facebook/m2m100_1.2B
 
+```python
+import ctranslate2
+import transformers
+
+translator = ctranslate2.Translator("m2m100_PARAMS")
+tokenizer = transformers.AutoTokenizer.from_pretrained("facebook/m2m100_PARAMS")
+tokenizer.src_lang = "en"
+
+source = tokenizer.convert_ids_to_tokens(tokenizer.encode("Hello world!"))
+target_prefix = [tokenizer.lang_code_to_token["de"]]
+results = translator.translate_batch([source], target_prefix=[target_prefix])
+target = results[0].hypotheses[0][1:]
+
+print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))
+```
+
+Alternative:
 pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0
 
 Checkpoint compatible to ctranslate2 and hf-hub-ctranslate2
 
 compute_type=int8_float16 for device="cuda"
 compute_type=int8 for device="cpu"
-```
+```python
 from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
 
-model_name = "michaelfeil/ct2fast-m2m100_1.2B"
+model_name = "michaelfeil/ct2fast-m2m100_PARAMS"
 model = TranslatorCT2fromHfHub(
         # load in int8 on CUDA
         model_name_or_path=model_name, 
         device="cuda",
         compute_type="int8_float16"
 )
-model.tokenizer = AutoTokenizer.from_pretrained("facebook/m2m100_1.2B")
+model.tokenizer = AutoTokenizer.from_pretrained("facebook/m2m100_PARAMS")
 outputs = model.generate(
     text=["Translate to german: How are you doing?"],
     min_decoding_length=24,