initial

app.py

@@ -1,64 +1,27 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from gradio.components import textbox
+from huggingface_hub import hf_hub_download
 
-"""
-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(model="igor-im/flux_prompt_expander")
+from vllm import LLM, SamplingParams
 
+def run_gguf_inference(prompt):
+    PROMPT_TEMPLATE = "<|user|>\n{prompt}</s>\n<|assistant|>\n"  # noqa: E501
+    prompt = PROMPT_TEMPLATE.format(prompt=prompt)
+    # Create a sampling params object.
+    sampling_params = SamplingParams(temperature=0, max_tokens=128)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Create an LLM.
+    llm = LLM(model="igor-im/flux_prompt_expander",
+              tokenizer="igor-im/flux_prompt_expander",
+              gpu_memory_utilization=0.95)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    outputs = llm.generate(prompt, sampling_params)
+    # Print the outputs.
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
 
-    messages.append({"role": "user", "content": message})
+interface = gr.Interface(fn=run_gguf_inference, inputs='textbox', outputs='textbox')
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+interface.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+transformers
+vllm