Create README.md

README.md

@@ -0,0 +1,18 @@
+This is a finetuned version of Facebook/M2M100. 
+It has been trained on a parallel corpus on several Chinese video games translations. All of them are from human/fan translations.
+
+Sample generation script : 
+
+```from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+tokenizer = transformers.AutoTokenizer.from_pretrained(r"path\to\checkpoint")
+model = AutoModelForSeq2SeqLM.from_pretrained(r"path\to\checkpoint")
+tokenizer.src_lang = "zh"
+tokenizer.tgt_lang = "en"
+test_string = "地阶上品遁术，施展后便可立于所持之剑上，以极快的速度自由飞行。"
+
+inputs = tokenizer(test_string, return_tensors="pt")
+translated_tokens = model.generate(**inputs, num_beams=10, do_sample=True)
+translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
+
+print("CH : ", test_string , " // EN : ", translation)```
+