Upload folder using huggingface_hub

app.py

@@ -1,15 +1,30 @@
 import gradio as gr
 from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the Mistral-7B-v0.1 model and tokenizer
+model_name = "mistralai/Mistral-7B-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
 
 # Load the llama2 LLM model
 # model = pipeline("text-generation", model="llamalanguage/llama2", tokenizer="llamalanguage/llama2")
-model = pipeline("text-generation", model="meta-llama/Llama-2-7b-chat-hf", tokenizer="meta-llama/Llama-2-7b-chat-hf")
+# model = pipeline("text-generation", model="mistralai/Mistral-7B-v0.1", tokenizer="meta-llama/Llama-2-7b-chat-hf")
 
 # Define the chat function that uses the LLM model
+# def chat_interface(input_text):
+#     response = model(input_text, max_length=100, return_full_text=True)[0]["generated_text"]
+#     response_words = response.split()
+#     return response_words
+
+# Define the chat function that uses the Mistral-7B-v0.1 model
 def chat_interface(input_text):
-    response = model(input_text, max_length=100, return_full_text=True)[0]["generated_text"]
-    response_words = response.split()
-    return response_words
+    inputs = tokenizer.encode(input_text, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=100)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
 
 # Create the Gradio interface
 iface = gr.Interface(