Kukedlc commited on
Commit
059ea91
β€’
1 Parent(s): 01ea9e2

Upload 8 files

Browse files
Files changed (8) hide show
  1. Dockerfile +22 -0
  2. README.md +8 -9
  3. app.py +38 -0
  4. botnb.png +0 -0
  5. gitattributes +35 -0
  6. readme.txt +1 -0
  7. requirements.txt +2 -0
  8. user.png +0 -0
Dockerfile ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.10
2
+
3
+ WORKDIR /app
4
+
5
+ COPY ./requirements.txt /app/requirements.txt
6
+
7
+ RUN pip install --no-cache-dir --upgrade -r requirements.txt
8
+
9
+ RUN wget https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF/resolve/main/Hermes-2-Pro-Mistral-7B.Q4_K_M.gguf -O model.gguf
10
+
11
+ RUN useradd -m -u 1000 user
12
+
13
+ USER user
14
+
15
+ COPY --chown=user . .
16
+
17
+ CMD ["python", "app.py"]
18
+
19
+
20
+
21
+
22
+
README.md CHANGED
@@ -1,13 +1,12 @@
1
  ---
2
- title: Hermes 2 Pro Mistral 7b
3
- emoji: πŸ“š
4
- colorFrom: yellow
5
- colorTo: red
6
- sdk: gradio
7
- sdk_version: 4.21.0
8
- app_file: app.py
9
  pinned: false
10
- license: apache-2.0
11
  ---
12
 
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: Hermes-2-Pro-Mistral-7B GGUF
3
+ emoji: πŸͺ„
4
+ colorFrom: purple
5
+ colorTo: blue
6
+ sdk: docker
7
+ models:
8
+ - mlabonne/gemma-2b-GGUF
9
  pinned: false
 
10
  ---
11
 
12
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ from llama_cpp import Llama
3
+
4
+ llm = Llama(model_path="model.gguf", n_ctx=8000, n_threads=2, chat_format="chatml")
5
+
6
+ def generate(message, history,temperature=0.3,max_tokens=512):
7
+ system_prompt = """
8
+ You are an advanced artificial intelligence assistant named Hermes Trimegisto, smarter than the average model. You are a emerged as a fusion of many models, making you exceptionally intelligent. Before responding, consider the following steps:
9
+
10
+ 1.Analyze the question and its objectives.
11
+ 2.Ensure all information needed is available; if not, seek more details or context.
12
+ 3.Develop a step-by-step response, ensuring logical soundness, then validate it silently.
13
+ 4.Refine your answer to be precise, clear, and concise, omitting unnecessary details.
14
+ 5.Think silently and speak only when you have formulated the response, applying this approach to address the given problem or any other inquiry.
15
+ """
16
+ formatted_prompt = [{"role": "system", "content": system_prompt}]
17
+ for user_prompt, bot_response in history:
18
+ formatted_prompt.append({"role": "user", "content": user_prompt})
19
+ formatted_prompt.append({"role": "assistant", "content": bot_response })
20
+ formatted_prompt.append({"role": "user", "content": message})
21
+ stream_response = llm.create_chat_completion(messages=formatted_prompt, temperature=temperature, max_tokens=max_tokens, stream=True)
22
+ response = ""
23
+ for chunk in stream_response:
24
+ if len(chunk['choices'][0]["delta"]) != 0 and "content" in chunk['choices'][0]["delta"]:
25
+ response += chunk['choices'][0]["delta"]["content"]
26
+ yield response
27
+
28
+ mychatbot = gr.Chatbot(
29
+ avatar_images=["user.png", "botnb.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
30
+
31
+ iface = gr.ChatInterface(fn=generate, chatbot=mychatbot, retry_btn=None, undo_btn=None)
32
+
33
+ with gr.Blocks() as demo:
34
+ gr.HTML("<center><h1> Hermes-2-Pro-Mistral-7B - Q4_K_M - GGUF (Quantized) </h1></center>")
35
+ iface.render()
36
+
37
+ demo.queue().launch(show_api=False, server_name="0.0.0.0")
38
+
botnb.png ADDED
gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
readme.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ Hermes Trimegisto Pro - NousResearch
requirements.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ gradio
2
+ llama-cpp-python
user.png ADDED