Create app.py

app.py

@@ -0,0 +1,66 @@
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelWithLMHead
+
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
+@st.cache_data
+def load_model(model_name):
+    model = AutoModelWithLMHead.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
+    return model
+
+model = load_model("mistralai/Mixtral-8x7B-Instruct-v0.1")
+
+def infer(input_ids, max_length, temperature, top_k, top_p):
+
+    output_sequences = model.generate(
+        input_ids=input_ids,
+        max_length=max_length,
+        temperature=temperature,
+        top_k=top_k,
+        top_p=top_p,
+        do_sample=True,
+        num_return_sequences=1
+    )
+
+    return output_sequences
+default_value = "Ask me anything!"
+
+#prompts
+st.title("Chatbot")
+
+sent = st.text_area("Message", default_value, height = 100)
+max_length = st.sidebar.slider("Max Length", min_value = 10, max_value=30)
+temperature = st.sidebar.slider("Temperature", value = 1.0, min_value = 0.0, max_value=1.0, step=0.05)
+top_k = st.sidebar.slider("Top-k", min_value = 0, max_value=5, value = 0)
+top_p = st.sidebar.slider("Top-p", min_value = 0.0, max_value=1.0, step = 0.05, value = 0.9)
+
+encoded_prompt = tokenizer.encode(sent, add_special_tokens=False, return_tensors="pt")
+if encoded_prompt.size()[-1] == 0:
+    input_ids = None
+else:
+    input_ids = encoded_prompt
+
+
+output_sequences = infer(input_ids, max_length, temperature, top_k, top_p)
+
+
+
+for generated_sequence_idx, generated_sequence in enumerate(output_sequences):
+    print(f"=== GENERATED SEQUENCE {generated_sequence_idx + 1} ===")
+    generated_sequences = generated_sequence.tolist()
+
+    # Decode text
+    text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)
+
+    # Remove all text after the stop token
+    #text = text[: text.find(args.stop_token) if args.stop_token else None]
+
+    # Add the prompt at the beginning of the sequence. Remove the excess text that was used for pre-processing
+    total_sequence = (
+        sent + text[len(tokenizer.decode(encoded_prompt[0], clean_up_tokenization_spaces=True)) :]
+    )
+
+    generated_sequences.append(total_sequence)
+    print(total_sequence)
+
+
+st.write(generated_sequences[-1])