Update README.md

README.md

@@ -13,7 +13,11 @@ pipeline_tag: text-generation
 
 # 🐷SUS-Chat: Instruction tuning done right
 
+<p align="left">
+<a href="README_CN.md">中文</a>&nbsp ｜ &nbspEnglish&nbsp
+</p>
 
+<br><br>
 
 <div align="center">
 
@@ -83,14 +87,15 @@ pipeline_tag: text-generation
 # Inrtoduction
 
 <img src="https://hackmd.io/_uploads/HJlDtzhBa.png" id="fig-sus"
-alt="Figure 1: DALL·E 2023-12-01 11.03.28 - An imposing, majestic wild boar combined with elements of a futuristic transformer robot. The boar itself should be intricately blended with these tra" />
+alt="Figure 1: DALL·E 2023-12-01 11.03.28 - An imposing, majestic wild boar combined with elements of a futuristic transformer robot. The boar itself should be intricately blended with these tra" />
 
 **SUS-Chat** is a 34B bilingual Chinese-English dialogue model, jointly
 released by the **Southern University of Science and Technology** and
-**Cognitive Computing and Natural Language Center of International Digital Economy Academy (IDEA-CCNL)**. The SUS-Chat-34B model has
-been fine-tuned on millions of high-quality, multilingual instruction
-data. While maintaining the strong language capabilities of the base
-model, the SUS-Chat-34B model has improved the model’s response to human
+**Cognitive Computing and Natural Language Center of International
+Digital Economy Academy (IDEA-CCNL)**. The SUS-Chat-34B model has been
+fine-tuned on millions of high-quality, multilingual instruction data.
+While maintaining the strong language capabilities of the base model,
+the SUS-Chat-34B model has improved the model’s response to human
 instructions through high-quality instruction fine-tuning and excels at
 imitating human thought processes through chains of thought. It
 introduces inter-instruction attention sharing in long texts, expanding
@@ -142,7 +147,7 @@ similar scale and achieved the most advanced comprehensive performance.
 
 <img
 src="https://github.com/SUSTech-IDEA/SUS-Chat/raw/main/assets/radar.png"
-id="fig-bench" alt="Figure 2: Benchmark" />
+id="fig-bench" alt="Figure 2: Benchmark" />
 
 # Usage
 
@@ -174,10 +179,12 @@ model = AutoModelForCausalLM.from_pretrained(
 
 messages = [{"role": "user", "content": "hi"}]
 
-input_ids = tokenizer.encode(chat_template(messages), return_tensors="pt").to("cuda")
-output_ids = model.generate(input_ids.to("cuda"))
+input_ids = tokenizer.encode(
+    chat_template(messages), return_tensors="pt", add_special_tokens=False
+).to("cuda")
+output_ids = model.generate(input_ids.to("cuda"), max_length=256)
 response = tokenizer.decode(
-    output_ids[0][input_ids.shape[1] :], skip_special_tokens=True
+    output_ids[0][input_ids.shape[1] :], skip_special_tokens=False
 )
 
 messages.append({"role": "assistant", "content": response})
@@ -186,10 +193,12 @@ messages.append({"role": "assistant", "content": response})
 
 messages.append({"role": "user", "content": "What is the capital of China?"})
 
-input_ids = tokenizer.encode(chat_template(messages), return_tensors="pt").to("cuda")
-output_ids = model.generate(input_ids.to("cuda"))
+input_ids = tokenizer.encode(
+    chat_template(messages), return_tensors="pt", add_special_tokens=False
+).to("cuda")
+output_ids = model.generate(input_ids.to("cuda"), max_length=256)
 response = tokenizer.decode(
-    output_ids[0][input_ids.shape[1] :], skip_special_tokens=True
+    output_ids[0][input_ids.shape[1] :], skip_special_tokens=False
 )
 
 messages.append({"role": "assistant", "content": response})