Merge branch 'main' of https://huggingface.co/hsb06/toghetherAi-model

.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

app.py

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 from flask import Flask, request, jsonify
 from flask_cors import CORS
 import torch
@@ -69,3 +70,76 @@ if __name__ == "__main__":
     port = int(os.getenv("PORT", 5000))
     logging.info(f"Starting Flask app on port {port}")
     app.run(debug=True, host="0.0.0.0", port=port)
+=======
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import logging
+import os
+
+# Logging setup
+logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Hugging Face Model Hub Repository
+MODEL_REPO = "./"  # Replace with your Hugging Face model repo name
+
+# Load tokenizer and model from Hugging Face Model Hub
+try:
+    logging.info("Loading model and tokenizer from Hugging Face Model Hub...")
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
+    dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
+    model = AutoModelForCausalLM.from_pretrained(MODEL_REPO, torch_dtype=dtype).to(
+        "cuda" if torch.cuda.is_available() else "cpu"
+    )
+    logging.info("Model loaded successfully.")
+except Exception as e:
+    logging.error("Failed to load the model or tokenizer.", exc_info=True)
+    raise e
+
+# Flask app initialization
+app = Flask(__name__)
+CORS(app)  # Enable CORS
+
+def generate_response(prompt):
+    """Generate a response from the model given a prompt."""
+    try:
+        logging.debug(f"Generating response for prompt: {prompt}")
+        inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+        input_length = inputs.input_ids.shape[1]
+        outputs = model.generate(
+            **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+        )
+        token = outputs.sequences[0, input_length:]
+        output_str = tokenizer.decode(token, skip_special_tokens=True)
+        logging.debug(f"Generated response: {output_str}")
+        return output_str
+    except Exception as e:
+        logging.error("Error during response generation", exc_info=True)
+        return "Sorry, I encountered an error while generating the response."
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    """Endpoint to handle chat requests."""
+    try:
+        logging.debug("Received a POST request to /chat")
+        data = request.json
+        logging.debug(f"Request data: {data}")
+
+        if not data or "message" not in data:
+            return jsonify({"error": "Invalid request. 'message' field is required."}), 400
+
+        user_input = data.get("message", "")
+        prompt = f"<human>: {user_input}\n<bot>:"
+        response = generate_response(prompt)
+        return jsonify({"response": response}), 200
+    except Exception as e:
+        logging.error("Error in /chat endpoint", exc_info=True)
+        return jsonify({"error": "Internal server error", "message": str(e)}), 500
+
+if __name__ == "__main__":
+    # Get the port from environment variable or default to 5000
+    port = int(os.getenv("PORT", 5000))
+    logging.info(f"Starting Flask app on port {port}")
+    app.run(debug=True, host="0.0.0.0", port=port)
+>>>>>>> 6ff0da104f5a2eb5ee298dc0164db0c0b16215e2

config.json

@@ -22,4 +22,4 @@
   "use_cache": true,
   "use_parallel_residual": false,
   "vocab_size": 50432
-}
+}

generation_config.json

@@ -3,4 +3,4 @@
   "bos_token_id": 0,
   "eos_token_id": 0,
   "transformers_version": "4.28.1"
-}
+}

special_tokens_map.json

@@ -2,4 +2,4 @@
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
-}
+}

tokenizer_config.json

@@ -1,3 +1,4 @@
+<<<<<<< HEAD
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
@@ -7,3 +8,14 @@
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }
+=======
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}
+>>>>>>> 6ff0da104f5a2eb5ee298dc0164db0c0b16215e2