Add pipeline tag and library name

This PR ensures the "how to use" button appears on the top right of the model card (with a Transformers example).
It also adds the appropriate pipeline tag, ensuring that it can be found at https://huggingface.co/models?pipeline_tag=text-generation&sort=trending.

README.md

@@ -1,7 +1,4 @@
 ---
-license: other
-license_name: seallm
-license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
 language:
 - en
 - zh
@@ -28,12 +25,16 @@ language:
 - fa
 - tl
 - my
+license: other
+license_name: seallm
+license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - multilingual
 - babel
 ---
 
-
 # *Babel*: Open Multilingual Large Language Models Serving Over 90% of Global Speakers
 
 <p align="center">
@@ -108,8 +109,10 @@ messages = [
 
 text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 model_inputs = tokenizer([text], return_tensors="pt").to(device)
-print(f"Formatted text:\n {text}")
-print(f"Model input:\n {model_inputs}")
+print(f"Formatted text:
+ {text}")
+print(f"Model input:
+ {model_inputs}")
 
 generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512, do_sample=True, eos_token_id=tokenizer.eos_token_id)
 generated_ids = [
@@ -117,7 +120,8 @@ generated_ids = [
 ]
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
 
-print(f"Response:\n {response[0]}")
+print(f"Response:
+ {response[0]}")
 ```
 
 ### Performance of 10B-Size Instruct Models vs. Babel-9B-Chat