Update app.py

app.py

@@ -1,23 +1,21 @@
 import gradio as gr
-from llama_cpp import Llama
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-llm = Llama(
-    model_path="deepseek-coder-6.7b.Q4_K_M.gguf",
-    n_ctx=2048,
-    n_threads=4
+model_id = "deepseek-ai/deepseek-coder-6.7b-instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.float16,
+    trust_remote_code=True
 )
 
 def chat(prompt):
-    system_prompt = "You are a helpful coding assistant. Answer precisely."
-    full_prompt = f"### Instruction:\n{prompt}\n### Response:\n"
-    output = llm(full_prompt, max_tokens=1024)
-    return output["choices"][0]["text"]
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
 
-gr.Interface(
-    fn=chat,
-    inputs="text",
-    outputs="text",
-    title="DeepSeek Coder 6.7B",
-    description="Free ChatGPT-style coding assistant",
-    theme="soft"
-).launch()
+gr.Interface(fn=chat, inputs="text", outputs="text", title="DeepSeek Coder 6.7B Chatbot").launch()