Update app.py

app.py

@@ -13,6 +13,12 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 token=os.getenv('token')
 print('token = ',token)
 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "mistralai/Mistral-7B-v0.3"
+tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
+
+model = AutoModelForCausalLM.from_pretrained(model_id, token= token)
 
 
 
@@ -26,24 +32,11 @@ def respond(
     temperature,
     top_p,
 ):
-    from transformers import AutoTokenizer, AutoModelForCausalLM
-
-    model_id = "CohereForAI/c4ai-command-r-plus-4bit"
-
-    tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
-    model = AutoModelForCausalLM.from_pretrained(model_id, token= token)
-    messages = [{"role": "user", "content": "Hello, how are you?"}]
-    input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
-
-    gen_tokens = model.generate(
-    input_ids, 
-    max_new_tokens=100, 
-    do_sample=True, 
-    temperature=0.3,
-    )
+    inputs = tokenizer("Hello my name is", return_tensors="pt")
 
-    gen_text = tokenizer.decode(gen_tokens[0])
+    outputs = model.generate(**inputs, max_new_tokens=20)
+    gen_text=tokenizer.decode(outputs[0], skip_special_tokens=True
+   
     print(gen_text)
     yield gen_text
     # for val in history: