main-model-407

.gitignore

@@ -0,0 +1 @@
+__pycache__

app.py

@@ -1,64 +1,4 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-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)",
-        ),
-    ],
-)
-
+from templates import demo
 
 if __name__ == "__main__":
     demo.launch()

models/best_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40918ad8d7c870738ea912267df1b45a4e4b12715b59624ab4043deeb0909d1
+size 32753848

models/tokenizer_input.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b3843c10879971954f83a50fa1026c482d337806fa8d60423db8c8fd1a1cbe
+size 2900

models/tokenizer_target.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b34ae5502ddfaebfc273aba8af102c9807cf5ee91aeb601dd0d2aaf4396dc4b
+size 1961

requirements.txt

@@ -1 +1,93 @@
-huggingface_hub==0.25.2
+absl-py==2.3.1
+aiofiles==24.1.0
+annotated-types==0.7.0
+anyio==4.9.0
+astunparse==1.6.3
+bert-score==0.3.13
+certifi==2025.6.15
+charset-normalizer==3.4.2
+click==8.2.1
+colorama==0.4.6
+contourpy==1.3.2
+cycler==0.12.1
+fastapi==0.115.14
+ffmpy==0.6.0
+filelock==3.18.0
+flatbuffers==25.2.10
+fonttools==4.58.5
+fsspec==2025.5.1
+gast==0.6.0
+google-pasta==0.2.0
+gradio==5.35.0
+gradio_client==1.10.4
+groovy==0.1.2
+grpcio==1.73.1
+h11==0.16.0
+h5py==3.14.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.33.2
+idna==3.10
+Jinja2==3.1.6
+joblib==1.5.1
+keras==3.10.0
+kiwisolver==1.4.8
+libclang==18.1.1
+Markdown==3.8.2
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.3
+mdurl==0.1.2
+ml_dtypes==0.5.1
+mpmath==1.3.0
+namex==0.1.0
+networkx==3.5
+nltk==3.9.1
+numpy==2.1.3
+opt_einsum==3.4.0
+optree==0.16.0
+orjson==3.10.18
+packaging==25.0
+pandas==2.3.0
+pillow==11.3.0
+protobuf==5.29.5
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.4
+rich==14.0.0
+ruff==0.12.2
+safehttpx==0.1.6
+safetensors==0.5.3
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.46.2
+sympy==1.14.0
+tensorboard==2.19.0
+tensorboard-data-server==0.7.2
+tensorflow==2.19.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==3.1.0
+tokenizers==0.21.2
+tomlkit==0.13.3
+torch==2.7.1
+tqdm==4.67.1
+transformers==4.53.0
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.35.0
+websockets==15.0.1
+Werkzeug==3.1.3
+wrapt==1.17.2

templates.py

@@ -0,0 +1,13 @@
+import gradio as gr
+from utils import chatbot
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 Chatbot LSTM dengan Gradio")
+    chatbot_output = gr.Chatbot()
+    msg = gr.Textbox(label="Ketik pesan Anda dan tekan Enter")
+    clear = gr.Button("🔄 Bersihkan Riwayat")
+
+    state = gr.State([])
+
+    msg.submit(chatbot, [msg, state], [msg, chatbot_output, state])
+    clear.click(lambda: ([], []), None, [chatbot_output, state])

utils.py

@@ -0,0 +1,92 @@
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import load_model
+import pickle
+import numpy as np
+
+# model yang ingin dimuat
+def load_models(path_model, path_tokenizer_input, path_tokenizer_output):
+    model = load_model(path_model, compile=True)
+
+    with open(path_tokenizer_input, 'rb') as f:
+        tokenizer_inputs = pickle.load(f)
+
+    with open(path_tokenizer_output, 'rb') as f:
+        tokenizer_outputs = pickle.load(f)
+
+    return model, tokenizer_inputs, tokenizer_outputs
+
+# kalkulasi sample temperature agar lebih hangat generatif nya
+def sample_with_temperature(probs, temperature=1.0, top_k=None):
+    if temperature != 1.0:
+        probs = np.log(probs) / temperature
+        probs = np.exp(probs)
+        probs = probs / np.sum(probs)
+    
+    if top_k is not None:
+        top_k_indices = np.argpartition(probs, -top_k)[-top_k:]
+        top_k_probs = probs[top_k_indices]
+        top_k_probs = top_k_probs / np.sum(top_k_probs)  # Renormalize
+        sampled_index = np.random.choice(top_k_indices, p=top_k_probs)
+    else:
+        sampled_index = np.random.choice(len(probs), p=probs)
+    
+    return sampled_index
+
+# fungsi prediksi teks
+def predict_with_main_model(user_text, tokenizer_input, tokenizer_target, model,
+                            max_len=15, temperature=1.0, top_k=None, max_encoder_len=9, max_decoder_len=15):
+    if max_len is None:
+        max_len = max_decoder_len  
+
+    input_seq = tokenizer_input.texts_to_sequences([user_text])
+    encoder_input = pad_sequences(input_seq, maxlen=max_encoder_len, padding='post')
+
+    start_token = tokenizer_target.word_index.get('<sos>', 1)
+    end_token = tokenizer_target.word_index.get('<eos>', 2)
+
+    decoder_input = np.zeros((1, max_len - 1), dtype='int32')
+    decoder_input[0, 0] = start_token
+
+    decoded_tokens = []
+
+    for i in range(1, max_len - 1):
+        predictions = model.predict([encoder_input, decoder_input], verbose=0)
+        token_probs = predictions[0, i - 1]
+
+        if top_k:
+            token_id = sample_with_temperature(token_probs, temperature, top_k)
+        else:
+            token_id = np.argmax(token_probs)
+
+        if token_id == end_token:
+            break
+
+        word = tokenizer_target.index_word.get(token_id, '')
+        if word and word != '<sos>':
+            decoded_tokens.append(word)
+
+        decoder_input[0, i] = token_id
+    return ' '.join(decoded_tokens)
+
+# ada penambahan riwayat pesan (memori)
+def chatbot(user_message, histories):
+    histories = histories or []
+
+    model, tokenizer_inputs, tokenizer_outputs = load_models(
+        "models/best_model.h5",
+        "models/tokenizer_input.pkl",
+        "models/tokenizer_target.pkl"
+    )
+
+    response = predict_with_main_model(
+        user_message,
+        tokenizer_inputs,
+        tokenizer_outputs,
+        model,
+        temperature=1.0,
+        top_k=10
+    )
+
+    histories.append(("👤: " + user_message, "🤖: " + response))
+
+    return "", histories, histories