feat: add mistral

app.py

@@ -1,8 +1,8 @@
 import spaces
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+# model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", device_map="auto")
+# tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
 
 # # Check if a GPU is available
 # device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -39,6 +39,7 @@ def retriever_qa(file, query):
         {"role": "user", "content": first_line}
     ]
 
+    tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
     model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
 
     generated_ids = llm.generate(model_inputs, max_new_tokens=100, do_sample=True)