Update app.py

app.py

@@ -7,7 +7,7 @@ import gradio as gr
 tokenizer = AutoTokenizer.from_pretrained(
     "Kaludi/chatgpt-gpt4-prompts-bart-large-cnn-samsum")
 model = AutoModelForSeq2SeqLM.from_pretrained(
-    "Kaludi/chatgpt-gpt4-prompts-bart-large-cnn-samsum")
+    "Kaludi/chatgpt-gpt4-prompts-bart-large-cnn-samsum", from_tf=True)
 
 # zephyr
 pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-alpha",
@@ -26,8 +26,8 @@ def useZephyr(prompt):
     prompt = pipe.tokenizer.apply_chat_template(
         messages, tokenize=False, add_generation_prompt=True)
 
-    outputs = pipe(prompt, max_new_tokens=256, do_sample=True,
-                   temperature=0.7, top_k=50, top_p=0.95)
+    # outputs = pipe(prompt, max_new_tokens=256, do_sample=True,temperature=0.7, top_k=50, top_p=0.95)
+    outputs = pipe(prompt)
     return outputs[0]["generated_text"]
 
 
@@ -38,17 +38,6 @@ def generatePrompt(prompt):
     prompt = output[0]
 
     return useZephyr(prompt)
-
-
-def generate_test(prompt):
-    batch = tokenizer(prompt, return_tensors="pt")
-    generated_ids = model.generate(batch["input_ids"], max_new_tokens=150)
-    output = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-    return output[0]
-
-
-def generate_prompt(prompt, max_new_tokens):
-    return generatePrompt(prompt, max_new_tokens)
 #
 
 # Interface