added codeqwen inference code

app.py

@@ -1,64 +1,47 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+import transformers
+
+# Load the model and tokenizer
+model_name = "Qwen/CodeQwen1.5-7B-Chat"
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
+max_new_tokens:int=2048
+do_sample:bool=True
+num_beams:int=1
+temperature:float=0.5
+top_p:float=0.95
+top_k:float=40
+repetition_penalty:float=1.1
+pipe = transformers.pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        max_new_tokens=max_new_tokens,
+        do_sample=do_sample,
+        num_beams=num_beams,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+        top_k=top_k,
+        repetition_penalty=repetition_penalty,
+    )
+
+def generate_response(input_text):
+    messages = [
+                {
+                    "role": "system", "content": "You are a helpful coding chatbot. You will answer the user's questions to the best of your ability.",
+                    "role": "user", "content": input_text,
+                },
+        ]
+    return pipe(messages)[0]['generated_text'][-1]['content'].replace("\\n", "\n")
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_response, 
+    inputs="text", 
+    outputs="text",
+    title="Artigenz Coder - 6.7B Model",
+    description="A code-generation model from Artigenz. Enter a prompt to get code suggestions or completions."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()

requirements.txt

@@ -1 +1,20 @@
-huggingface_hub==0.25.2
+certifi==2024.8.30
+charset-normalizer==3.4.0
+filelock==3.16.1
+fsspec==2024.10.0
+huggingface-hub==0.25.2
+idna==3.10
+numpy==2.1.3
+packaging==24.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+safetensors==0.4.5
+tokenizers==0.20.3
+tqdm==4.67.0
+transformers==4.46.2
+typing_extensions==4.12.2
+urllib3==2.2.3
+--find-links https://download.pytorch.org/whl/torch_stable.html
+torch
+accelerate>=0.26.0