Update README.md

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+license: mit
+language:
+- en
+- zh
+---
+
+Github: https://github.com/jasonNLP/TAT-R1
+
+## Quickstart
+Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "hhoh/TAT-R1"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+
+system_prompt = """A conversation between User and Assistant. The User asks a question, and the Assistant solves it. \
+The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. \
+The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, \
+i.e., <think> reasoning process here </think> <answer> answer here </answer>. \
+
+User:
+{}
+
+Assistant:
+"""
+
+# For English to Chinese translation, use:
+query = "Translate the flowing text into Chinese, do not explain：\n{}"
+# For Chinese to English translation, use:
+# query = "Translate the flowing text into English, do not explain：\n{}"
+
+src_text = "Plants make oxygen which humans breathe, and they take in carbon-dioxide which humans exhale (that is, breathe out)."
+prompt = system_prompt.format(query.format(src_text))
+
+
+model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=2048
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+
+```