add: bonito

app.py

@@ -5,7 +5,7 @@ from huggingface_hub import InferenceClient
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("BatsResearch/bonito-v1")
 
 
 @spaces.GPU
@@ -16,29 +16,30 @@ def respond(
     temperature,
     top_p,
 ):
-    # messages = [{"role": "system", "content": system_message}]
+    task_type = task_type.lower()
+    input_text = "<|tasktype|>\n" + task_type.strip()
+    input_text += "\n<|context|>\n" + message.strip() + "\n<|task|>\n"
 
-    # for val in history:
-    #     if val[0]:
-    #         messages.append({"role": "user", "content": val[0]})
-    #     if val[1]:
-    #         messages.append({"role": "assistant", "content": val[1]})
-    messages = []
-    messages.append({"role": "user", "content": message})
+    response = client.text_generation(input_text, max_length=max_tokens, temperature=temperature, top_p=top_p)
 
-    response = ""
+    return response
+    # messages = []
+    # messages.append({"role": "user", "content": message})
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # response = ""
 
-        response += token
-        yield response
+
+    # for message in client.text_generation(
+    #     messages,
+    #     max_tokens=max_tokens,
+    #     stream=True,
+    #     temperature=temperature,
+    #     top_p=top_p,
+    # ):
+    #     token = message.choices[0].delta.content
+
+    #     response += token
+    #     yield response
 
 
 """
@@ -77,6 +78,8 @@ task_types = [
     "textual entailment",
     "natural language inference",
 ]
+# capitalize for better readability
+task_types = [task_type.capitalize() for task_type in task_types]
 
 demo = gr.Interface(
     fn=respond,