Upload 8 files

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY ./requirements.txt /app/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+RUN wget https://huggingface.co/Kukedlc/ArchBeagle-7B-GGUF/resolve/main/archbeagle-7b.Q5_K_M.gguf -O model.gguf
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+COPY --chown=user . .
+
+CMD ["python", "app.py"]

README.md

@@ -1,12 +1,12 @@
 ---
-title: ArchBeagleCuantized
-emoji: 🏃
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 4.17.0
-app_file: app.py
+title: NeuralBeagle Chat
+emoji: 🐶
+colorFrom: purple
+colorTo: blue
+sdk: docker
+models:
+- mlabonne/NeuralBeagle14-7B
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+from llama_cpp import Llama
+
+llm = Llama(model_path="model.gguf", n_ctx=8000, n_threads=2, chat_format="chatml")
+  
+def generate(message, history,temperature=0.3,max_tokens=512):
+    system_prompt = "You are NeuralBeagle, a superintelligent AI assistant. "
+    formatted_prompt = [{"role": "system", "content": system_prompt}]
+    for user_prompt, bot_response  in history:
+        formatted_prompt.append({"role": "user", "content": user_prompt})
+        formatted_prompt.append({"role": "assistant", "content": bot_response })
+    formatted_prompt.append({"role": "user", "content": message})
+    stream_response = llm.create_chat_completion(messages=formatted_prompt, temperature=temperature, max_tokens=max_tokens, stream=True)
+    response  = ""
+    for chunk in stream_response:
+        if len(chunk['choices'][0]["delta"]) != 0 and "content" in chunk['choices'][0]["delta"]:
+            response  += chunk['choices'][0]["delta"]["content"]
+        yield response 
+
+mychatbot = gr.Chatbot(
+avatar_images=["user.png", "botnb.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
+        
+iface = gr.ChatInterface(fn=generate, chatbot=mychatbot, retry_btn=None, undo_btn=None)
+
+with gr.Blocks() as demo:
+    gr.HTML("<center><h1>ArchBeagle GGUF q_5_k_m By Maxime Labonne </h1></center>")
+    iface.render()
+
+demo.queue().launch(show_api=False, server_name="0.0.0.0")
+    

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

readme.txt

@@ -0,0 +1,2 @@
+I'd like to give thanks to Maxime Labonne for finetuning this model and TheBloke for providing its quantized version.
+Tomoniai

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+llama-cpp-python