Duplicate from moses132/dailydialog-chatbot

Co-authored-by: MUKIIBI MOSES <moses132@users.noreply.huggingface.co>

.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

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# -----------------------------
+# Model setup
+# -----------------------------
+model_name = "moses132/dailydialog-chatbot"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# -----------------------------
+# Chat function
+# -----------------------------
+chat_history = []
+
+def moses_chat(user_message):
+    # Add user message to history
+    chat_history.append(f"User: {user_message}")
+    
+    # Build prompt from chat history
+    prompt = "\n".join(chat_history) + "\nAI:"
+    
+    # Encode input
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    
+    # Generate model output
+    outputs = model.generate(
+        inputs,
+        max_length=200,
+        do_sample=True,
+        top_p=0.9,
+        temperature=0.8,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    
+    # Decode reply
+    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    reply_text = reply.replace(prompt, "").strip()
+    
+    # Add AI reply to history
+    chat_history.append(f"AI: {reply_text}")
+    
+    # Return all messages as chat bubbles
+    messages = []
+    for i, msg in enumerate(chat_history):
+        if msg.startswith("User:"):
+            messages.append(("User", msg.replace("User:","").strip()))
+        else:
+            messages.append(("AI", msg.replace("AI:","").strip()))
+    return messages
+
+# -----------------------------
+# Gradio Interface
+# -----------------------------
+with gr.Blocks(title="Moses Chat") as demo:
+    gr.Markdown("<h1 style='text-align:center; color:#4B0082;'>Moses Chat</h1>")
+    
+    with gr.Row():
+        chatbot = gr.Chatbot(elem_id="moses-chatbot").style(height=500)
+    
+    with gr.Row():
+        msg = gr.Textbox(placeholder="Type your message here...", lines=1)
+        submit = gr.Button("Send")
+    
+    def respond(message):
+        return moses_chat(message)
+    
+    submit.click(respond, inputs=msg, outputs=chatbot)
+    msg.submit(respond, inputs=msg, outputs=chatbot)
+
+# Launch the app
+demo.launch()

config.json

@@ -0,0 +1,48 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfe81e8c2b37f28ae44d3181cd0713d9c686da45b46f8332561313d8281ec9a
+size 327657928

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df1b297665771cac3a0d43a9e04d5208aafddd9e50629e3094e7f80a6fa7d57
+size 5201