Upload 4 files

README.md

@@ -1,13 +1,16 @@
 ---
-title: Math Chatbot 2
-emoji: 💬
-colorFrom: yellow
+title: Qwen2.5 Math 7B Instruct GGUF
+emoji: 📈
+colorFrom: blue
 colorTo: purple
 sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
 pinned: false
-license: apache-2.0
+license: gpl-3.0
+short_description: Runs Qwen2.5-Math-7B-Instruct-GGUF
+models:
+- bartowski/Qwen2.5-Math-7B-Instruct-GGUF
 ---
 
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,64 +1,125 @@
+import json
+import spaces
+import subprocess
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
 
+CSS = """
+#qwen-md .katex-display { display: inline; }
+#qwen-md .katex-display>.katex { display: inline; }
+#qwen-md .katex-display>.katex>.katex-html { display: inline; }
 """
-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
+
+hf_hub_download(
+    repo_id="bartowski/Qwen2.5-Math-7B-Instruct-GGUF",
+    filename="Qwen2.5-Math-7B-Instruct-Q6_K_L.gguf",
+    local_dir="./models",
+)
+
+llm = Llama(
+    model_path="models/Qwen2.5-Math-7B-Instruct-Q6_K_L.gguf",
+    flash_attn=True,
+    n_ctx=8192,
+    n_batch=1024,
+    chat_format="chatml",
+)
+
+# Gradio 组件
+output_md = gr.Markdown(
+    label="Answer",
+    value="Answer will be presented here",
+    latex_delimiters=[
+        {"left": "\\(", "right": "\\)", "display": True},
+        {"left": "\\begin\{equation\}", "right": "\\end\{equation\}", "display": True},
+        {"left": "\\begin\{align\}", "right": "\\end\{align\}", "display": True},
+        {"left": "\\begin\{alignat\}", "right": "\\end\{alignat\}", "display": True},
+        {"left": "\\begin\{gather\}", "right": "\\end\{gather\}", "display": True},
+        {"left": "\\begin\{CD\}", "right": "\\end\{CD\}", "display": True},
+        {"left": "\\[", "right": "\\]", "display": True},
+    ],
+    elem_id="qwen-md",
+    show_copy_button=True,
+    container=True,
+    render=False,
+)
+target_lang = gr.Dropdown(
+    choices=["Chinese", "English"],
+    value="Chinese",
+    label="Output Language",
+    interactive=True,
+    render=False,
+)
+new_tokens = gr.Slider(
+    minimum=1, maximum=8192, value=2048, step=1, label="Max new tokens", render=False
+)
+temperature = gr.Slider(
+    minimum=0, maximum=2.0, value=0.5, step=0.1, label="Temperature", render=False
+)
+top_p = gr.Slider(minimum=0.0, maximum=1.0, value=0.95, step=0.05, label="Top P", render=False)
+input_text = gr.Textbox(label="Ask math questions here", render=False)
+submit_btn = gr.Button(value="Ask", render=False)
+banner = gr.Markdown(value="""
+# 📖 Qwen2.5-Math GGUF
+This WebUI is based on Qwen2.5-Math-7B-Instruct-GGUF for mathematical reasoning. You can input texts of mathematical or arithmetic problems.
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+)
 
 
+# Gradio 函数
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    input_text,
+    lang="Chinese",
+    max_tokens=2048,
+    temperature=0.5,
+    top_p=0.95,
 ):
-    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})
+    if lang == "Chinese":
+        sys_msg = "你是一个乐于助人的数学助手. 你使用中文回答问题"
+    else:
+        sys_msg = "You are a helpful math assistant. You should always provide your answer in English."
+    messages = [
+        {
+            "role": "system",
+            "content": sys_msg,
+        },
+        {"role": "user", "content": input_text},
+    ]
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    response = llm.create_chat_completion(
+        messages=messages,
         stream=True,
+        max_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    )
+    message_repl = ""
+    for chunk in response:
+        if len(chunk['choices'][0]["delta"]) != 0 and "content" in chunk['choices'][0]["delta"]:
+            message_repl = message_repl + \
+                chunk['choices'][0]["delta"]["content"]
+        yield message_repl
 
 
-"""
-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)",
-        ),
-    ],
-)
-
+with gr.Blocks(css=CSS, theme="NoCrypt/miku") as demo:
+    submit_btn.click(
+        fn=respond,
+        inputs=[input_text, target_lang, new_tokens, temperature, top_p],
+        outputs=output_md,
+    )
+    with gr.Column():
+        banner.render()
+        with gr.Row():
+            with gr.Column():
+                input_text.render()
+                target_lang.render()
+                new_tokens.render()
+                temperature.render()
+                top_p.render()
+                submit_btn.render()
+            with gr.Column():
+                output_md.render()
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub
+scikit-build-core
+llama-cpp-python