Update README.md

README.md

@@ -124,32 +124,6 @@ To force the target language id as the first generated token, pass the `forced_b
 
 To install `sentencepiece` run `pip install sentencepiece`
 
-
-```python
-from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
-
-hi_text = "जीवन एक चॉकलेट बॉक्स की तरह है।"
-chinese_text = "生活就像一盒巧克力。"
-
-model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
-tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")
-
-# translate Hindi to French
-tokenizer.src_lang = "hi"
-encoded_hi = tokenizer(hi_text, return_tensors="pt")
-generated_tokens = model.generate(**encoded_hi, forced_bos_token_id=tokenizer.get_lang_id("fr"))
-tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
-# => "La vie est comme une boîte de chocolat."
-
-# translate Chinese to English
-tokenizer.src_lang = "zh"
-encoded_zh = tokenizer(chinese_text, return_tensors="pt")
-generated_tokens = model.generate(**encoded_zh, forced_bos_token_id=tokenizer.get_lang_id("en"))
-tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
-# => "Life is like a box of chocolate."
-```
-
-
 See the [model hub](https://huggingface.co/models?filter=m2m_100) to look for more fine-tuned versions.
 
 
@@ -167,4 +141,37 @@ Afrikaans (af), Amharic (am), Arabic (ar),  Asturian (ast), Azerbaijani (az), Ba
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```
+
+## How to download this model using python
+- Install Python https://www.python.org/downloads/
+- `cmd`
+- `python --version`
+- `python -m pip install huggingface_hub`
+- `python`
+
+```
+import huggingface_hub
+huggingface_hub.download_snapshot('entai2965/m2m100-418M-ctranslate2',local_dir='m2m100-418M-ctranslate2')
+```
+
+## How to run this model
+- https://opennmt.net/CTranslate2/guides/transformers.html#m2m-100
+- `cmd`
+- `python -m pip install ctranslate2 transformers`
+- `python`
+```
+import ctranslate2
+import transformers
+
+translator = ctranslate2.Translator("m2m100-418M-ctranslate2", device="cpu")
+tokenizer = transformers.AutoTokenizer.from_pretrained("m2m100-418M-ctranslate2",clean_up_tokenization_spaces=True)
+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)))
+```