Initial commit with fine-tuned GPT-2 model and Streamlit app

app.py

@@ -0,0 +1,45 @@
+
+import streamlit as st
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+import torch
+
+# Load the fine-tuned model and tokenizer
+model_name_or_path = "fine_tuned_model123"
+model = GPT2LMHeadModel.from_pretrained(model_name_or_path)
+tokenizer = GPT2Tokenizer.from_pretrained(model_name_or_path)
+
+# Move the model to GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+# Define the text generation function
+def generate_text(model, tokenizer, seed_text, max_length=100, temperature=1.0, num_return_sequences=1):
+    input_ids = tokenizer.encode(seed_text, return_tensors='pt').to(device)
+    with torch.no_grad():
+        output = model.generate(
+            input_ids,
+            max_length=max_length,
+            temperature=temperature,
+            num_return_sequences=num_return_sequences,
+            do_sample=True,
+            top_k=50,
+            top_p=0.95,
+        )
+    generated_texts = [tokenizer.decode(output[i], skip_special_tokens=True) for i in range(num_return_sequences)]
+    return generated_texts
+
+# Streamlit app
+st.title("Text Generation with GPT-2")
+st.write("This app generates text using a fine-tuned GPT-2 model. Enter a prompt and the model will generate a continuation.")
+st.info("This app's data is continuously improved, but it may still contain inaccuracies.")
+
+seed_text = st.text_input("Enter your prompt:", "Guvi is")
+max_length = st.slider("Max Length:", min_value=50, max_value=500, value=100)
+temperature = st.slider("Temperature:", min_value=0.1, max_value=2.0, value=1.0)
+
+if st.button("Generate"):
+    with st.spinner("Generating text..."):
+        generated_texts = generate_text(model, tokenizer, seed_text, max_length, temperature)
+        for i, generated_text in enumerate(generated_texts):
+            st.subheader(f"Generated Text {i + 1}")
+            st.write(generated_text)

fine_tuned_model123/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 0.1,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

fine_tuned_model123/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

fine_tuned_model123/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

fine_tuned_model123/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

requirements.txt

@@ -0,0 +1,4 @@
+
+transformers
+torch
+streamlit