auto causal model

app.py

@@ -1,12 +1,15 @@
 import gradio as gr
 import spaces
 from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 """
 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("BatsResearch/bonito-v1")
-
+# client = InferenceClient("BatsResearch/bonito-v1")
+model = AutoModelForCausalLM.from_pretrained("BatsResearch/bonito-v1")
+tokenizer = AutoTokenizer.from_pretrained("BatsResearch/bonito-v1")
+model.to("cuda")
 
 @spaces.GPU
 def respond(
@@ -20,7 +23,18 @@ def respond(
     input_text = "<|tasktype|>\n" + task_type.strip()
     input_text += "\n<|context|>\n" + message.strip() + "\n<|task|>\n"
 
-    response = client.text_generation(input_text, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)
+    input_ids = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
+    output = model.generate(
+        input_ids,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+        do_sample=True,
+    )
+
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    # response = client.text_generation(input_text, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)
 
     return response
     # messages = []