Add application file

app.py

@@ -0,0 +1,40 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+
+model_path = "inceptionai/Llama-3.1-Sherkala-8B-Chat"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.bfloat16, device_map="auto"
+)
+
+tokenizer.chat_template = "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+def chat_fn(user_input):
+    conversation = [{"role": "user", "content": user_input}]
+    input_ids = tokenizer.apply_chat_template(
+        conversation=conversation,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    ).to(device)
+
+    output_ids = model.generate(
+        input_ids,
+        max_new_tokens=512,
+        do_sample=True,
+        temperature=0.7
+    )
+    response = tokenizer.decode(output_ids[0][input_ids.shape[-1]:], skip_special_tokens=True)
+    return response
+
+gr.Interface(
+    fn=chat_fn,
+    inputs="text",
+    outputs="text",
+    title="Sherkala-8B Chat",
+    description="Multilingual LLaMA-3.1 based model (Kazakh, Russian, English)",
+    theme="default"
+).launch()