pierwszy commit

a.py

@@ -0,0 +1,8 @@
+from gradio_client import Client
+
+client = Client("wiklif/my-api")
+result = client.predict(
+		prompt="Jakie są 3 największe kraje? Pisz po polsku.",
+		api_name="/chat"
+)
+print(result)

app.py

@@ -1,7 +1,75 @@
+import spaces
 import gradio as gr
+import transformers
+import torch
 
-def greet(name):
-    return "Hello " + name + "!!"
+model_id = "meta-llama/Meta-Llama-3.1-8B"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+@spaces.GPU(duration=60)
+def load_pipeline():
+    return transformers.pipeline(
+        "text-generation",
+        model=model_id,
+        model_kwargs={"torch_dtype": torch.bfloat16},
+        device_map="auto"
+    )
+
+pipeline = load_pipeline()
+
+def generate_response(chat, kwargs):
+    output = pipeline(chat, **kwargs)[0]['generated_text']
+    if output.endswith("</s>"):
+        output = output[:-4]
+    return output
+
+def function(prompt, history=[]):
+    chat = "<s>"
+    for user_prompt, bot_response in history:
+        chat += f"[INST] {user_prompt} [/INST] {bot_response}</s> <s>"
+    chat += f"[INST] {prompt} [/INST]"
+
+    kwargs = dict(
+        max_new_tokens=4096,
+        do_sample=True,
+        temperature=0.5,
+        top_p=0.95,
+        repetition_penalty=1.0,
+        seed=1337
+    )
+
+    try:
+        output = generate_response(chat, kwargs)
+        return output
+    except:
+        return ''
+
+# Interfejs Gradio
+interface = gr.ChatInterface(
+    fn=function,
+    chatbot=gr.Chatbot(
+        avatar_images=None,
+        container=False,
+        show_copy_button=True,
+        layout='bubble',
+        render_markdown=True,
+        line_breaks=True
+    ),
+    css='h1 {font-size:22px;} h2 {font-size:20px;} h3 {font-size:18px;} h4 {font-size:16px;}',
+    autofocus=True,
+    fill_height=True,
+    analytics_enabled=False,
+    submit_btn='Chat',
+    stop_btn=None,
+    retry_btn=None,
+    undo_btn=None,
+    clear_btn=None
+)
+
+# API endpoint
+def api_predict(prompt):
+    return function(prompt)
+
+interface.launch(show_api=True, share=True)
+
+# Dodanie endpointu API
+gr.Interface(fn=api_predict, inputs="text", outputs="text").launch(share=True)

requirements.txt

@@ -0,0 +1,6 @@
+huggingface_hub
+gradio
+numpy<2
+torch
+transformers
+bitsandbytes