update mistral

app.py

@@ -1,41 +1,58 @@
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
-
-model_name = "Salesforce/codet5-base"
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# More complex C# code snippet
-code_snippet = """
-// This class demonstrates a simple calculator program
-public class Calculator {
-    // Adds two integers
-    public int Add(int a, int b) {
-        return a + b;
-    }
-
-    // Subtracts second integer from first
-    public int Subtract(int a, int b) {
-        return a - b;
-    }
-
-    // Multiplies two integers
-    public int Multiply(int a, int b) {
-        return a * b;
-    }
-
-    // Divides first integer by second
-    // Throws DivideByZeroException if b is zero
-    public int Divide(int a, int b) {
-        if (b == 0) {
-            throw new DivideByZeroException("Division by zero is not allowed.");
-        }
-        return a / b;
-    }
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+css = '''
+.gradio-container{max-width: 1000px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
 }
-"""
+'''
+
+client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
+def format_prompt(message, history, system_prompt=None):
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    if system_prompt:
+        prompt += f"[SYS] {system_prompt} [/SYS]"
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
+#Generate
+def generate(
+    prompt, history, system_prompt=None, temperature=0.2, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, history, system_prompt)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
+
 
-inputs = tokenizer(code_snippet, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=100)
-review = tokenizer.decode(outputs[0], skip_special_tokens=True)
+demo = gr.ChatInterface(
+    fn=generate,
+    css=css,
+    title="",
+    theme="bethecloud/storj_theme"
+)
 
-print("Code Review:", review)
+demo.queue().launch(show_api=False)