Initial Tamil Kavithai chatbot deployment

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+# Load the local Tamil GPT-2 model
+tokenizer = AutoTokenizer.from_pretrained("model")
+model = AutoModelForCausalLM.from_pretrained("model")
+
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def generate_kavithai(prompt):
+    if not prompt.strip():
+        return "தயவுசெய்து ஒரு வரியை உள்ளிடவும்..."
+    outputs = generator(prompt, max_length=50, num_return_sequences=1)
+    return outputs[0]["generated_text"]
+
+# Gradio UI setup
+interface = gr.Interface(
+    fn=generate_kavithai,
+    inputs=gr.Textbox(lines=2, placeholder="உங்கள் எண்ணத்தை இங்கே எழுதுங்கள்...", label="📝 உங்கள் வரிகள்"),
+    outputs=gr.Textbox(label="🎙️ கவிதை வெளியீடு"),
+    title="தமிழ் கவிதை AI Bot ✍️",
+    description="தமிழில் கவிதை உருவாக்கும் AI. உங்கள் வார்த்தைகளைப் பகிருங்கள் – ஒரு கவிதையை உருவாக்குவோம்!",
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    interface.launch()

loadmodel.py

@@ -0,0 +1,14 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Model name
+model_name = "abinayam/gpt-2-tamil"
+
+# Load from Hugging Face
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Save to local folder called 'model'
+model.save_pretrained("model")
+tokenizer.save_pretrained("model")
+
+print("✅ Model and tokenizer saved successfully in './model'")

model/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50265
+}

model/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "abinayam/gpt-2-tamil",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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": 300
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.49.0"
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1bed64b8bf4b6e42492c492d6f15af5018557be24fbab7edfefed65cd353d7
+size 497774208

model/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

model/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+datasets
+gradio
+accelerate