Upload 7 files

.gitattributes

@@ -1,35 +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
+*.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

Dockerfile

@@ -0,0 +1,24 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./main.py /code/main.py
+
+COPY ./space_checker.py /code/space_checker.py
+
+COPY ./requirements.txt /code/requirements.txt
+
+COPY ./start.sh /code/start.sh
+
+COPY . .
+
+RUN pip install -r /code/requirements.txt
+
+RUN chmod +x start.sh
+
+RUN sed -i 's/\r$//' start.sh
+
+CMD ["bash","start.sh"]

README.md

@@ -1,10 +1,11 @@
----
-title: MiniMax M1 Chat
-emoji: 😻
-colorFrom: indigo
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Minimax Text Chat
+emoji: 💬🗨️
+colorFrom: red
+colorTo: blue
+sdk: docker
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,163 @@
+import gevent.pywsgi
+from gevent import monkey;monkey.patch_all()
+from flask import Flask, request, Response, jsonify
+import argparse
+import requests
+import random
+import string
+import time
+import json
+import os
+
+app = Flask(__name__)
+app.json.sort_keys = False
+
+parser = argparse.ArgumentParser(description="An example of minimax demo with a similar API to OAI.")
+parser.add_argument("--host", type=str, help="Set the ip address.(default: 0.0.0.0)", default='0.0.0.0')
+parser.add_argument("--port", type=int, help="Set the port.(default: 7860)", default=7860)
+args = parser.parse_args()
+
+base_url = os.getenv('MODEL_BASE_URL')
+
+@app.route('/api/v1/models', methods=["GET", "POST"])
+@app.route('/v1/models', methods=["GET", "POST"])
+def model_list():
+    time_now = int(time.time())
+    model_list = {
+        "object": "list",
+        "data": [
+            {
+                "id": "MiniMax-Text-01",
+                "object": "model",
+                "created": time_now,
+                "owned_by": "minimax"
+            },
+            {
+                "id": "gpt-3.5-turbo",
+                "object": "model",
+                "created": time_now,
+                "owned_by": "openai"
+            }
+        ]
+    }
+    return jsonify(model_list)
+
+@app.route("/", methods=["GET"])
+def index():
+    return Response(f'Minimax OpenAI Compatible API<br><br>'+
+        f'Set "{os.getenv("SPACE_URL")}/api" as proxy (or API Domain) in your Chatbot.<br><br>'+
+        f'The complete API is: {os.getenv("SPACE_URL")}/api/v1/chat/completions')
+
+@app.route("/api/v1/chat/completions", methods=["POST", "OPTIONS"])
+@app.route("/v1/chat/completions", methods=["POST", "OPTIONS"])
+def chat_completions():
+
+    if request.method == "OPTIONS":
+        return Response(
+            headers={
+                "Access-Control-Allow-Origin": "*",
+                "Access-Control-Allow-Headers": "*",
+            }
+        )
+
+    data = request.get_json()
+    
+    # reorganize data
+    system = None
+    chat_history = []
+    prompt = ""
+    
+    if "messages" in data:
+        messages = data["messages"]
+        message_size = len(messages)
+        
+        prompt = messages[-1].get("content")
+        
+        # gen a random char(11) hash
+        chars = string.ascii_lowercase + string.digits
+        session_hash = "".join(random.choice(chars) for _ in range(10))
+        
+        single_prompt_data = {
+            'data': [
+                prompt,
+                None,
+            ],
+            'event_data': None,
+            'fn_index': 0,
+            'trigger_id': 7,
+            'session_hash': session_hash,
+        }
+        response = requests.post(f'{base_url}/gradio_api/run/predict', json=single_prompt_data)
+        
+        context_data = {
+            'data': [
+                None,
+                messages,
+                1000000,
+                data['temperature'],
+                data['top_p'],
+            ],
+            'event_data': None,
+            'fn_index': 2,
+            'trigger_id': 7,
+            'session_hash': session_hash,
+        }
+        response = requests.post(f'{base_url}/gradio_api/queue/join', json=context_data)
+        
+    def generate():
+
+        url = f"{base_url}/gradio_api/queue/data?session_hash={session_hash}"
+        data = requests.get(url, stream=True)
+
+        time_now = int(time.time())
+
+        for line in data.iter_lines():
+            if line:
+                decoded_line = line.decode("utf-8")
+                json_line = json.loads(decoded_line[6:])
+                if json_line["msg"] == "process_starts":
+                    res_data = gen_res_data({}, time_now=time_now, start=True)
+                    yield f"data: {json.dumps(res_data)}\n\n"
+                elif json_line["msg"] == "process_generating":
+                    res_data = gen_res_data(json_line, time_now=time_now)
+                    yield f"data: {json.dumps(res_data)}\n\n"
+                elif json_line["msg"] == "process_completed":
+                    yield "data: [DONE]"
+
+    return Response(
+        generate(),
+        mimetype="text/event-stream",
+        headers={
+            "Access-Control-Allow-Origin": "*",
+            "Access-Control-Allow-Headers": "*",
+        },
+    )
+
+
+def gen_res_data(data, time_now=0, start=False):
+    res_data = {
+        "id": "chatcmpl",
+        "object": "chat.completion.chunk",
+        "created": time_now,
+        "model": "MiniMax-Text-01",
+        "choices": [{"index": 0, "finish_reason": None}],
+    }
+
+    if start:
+        res_data["choices"][0]["delta"] = {"role": "assistant", "content": ""}
+    else:
+        chat_pair = data["output"]["data"][0]
+        
+        if chat_pair == []:
+            res_data["choices"][0]["finish_reason"] = "stop"
+        else:
+            try:
+                res_data["choices"][0]["delta"] = {"content": chat_pair[-1][-1]}
+            except:
+                res_data["choices"][0]["delta"] = {"content": chat_pair[-1]["content"]}
+    return res_data
+
+
+if __name__ == "__main__":
+    #app.run(host=args.host, port=args.port, debug=True)
+    gevent.pywsgi.WSGIServer((args.host, args.port), app).serve_forever()

requirements.txt

@@ -0,0 +1,3 @@
+flask
+requests
+gevent

space_checker.py

@@ -0,0 +1,13 @@
+import requests
+import time
+import os
+
+space_url = os.getenv('SPACE_URL')
+
+def fetch_url(url):
+    response = requests.get(url)
+    print(response.text)
+
+while True:
+    fetch_url(space_url)
+    time.sleep(3600)

start.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+python main.py &
+python space_checker.py &
+wait