added model

Gpt_neo_Epoch_10_Loss_031_data_5000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941e5b0ba78e59be1cf44737b967c6f1b03953330615f6af73bf8099beb6aa4d
+size 551214929

app.py

@@ -1,4 +1,69 @@
 import streamlit as st
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelWithLMHead
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+# device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
+device=torch.device("cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
+model=torch.load("Gpt_neo_Epoch_10_Loss_031_data_5000.pth",map_location=torch.device('cpu'))
+
+
+def predict_query(input_sentence,max_len=40,temp=0.7):
+    pred=[]
+    seq=tokenizer(input_sentence,return_tensors='pt')['input_ids'].to(device)
+    outputs=model.generate(seq,
+                          max_length=max_len,
+                          do_sample=True,
+                          top_p=0.95,
+                          #num_beams=5,
+                          temperature=temp,
+                          no_repeat_ngram_size=3,
+                          num_return_sequences=5
+                          ).to(device)
+    for i,out in enumerate(outputs):
+      out=tokenizer.decode(out, skip_special_tokens=True)
+      idx=out.find("<|sep|>")+7
+      out=out[idx:]
+      print(f"Sugestion{i} :{out}")
+      pred.append(tokenizer.decode(out, skip_special_tokens=True))
+    return pred
+# option = st.selectbox(
+#     'Please Select option',
+#    ('Predictive writing',"None"),index=1)
+
+
+st.title("Predictive scientific writing")
+st.write('### Using AI to Generate scientific literature')
+st.sidebar.markdown(
+    '''            
+    ## This is a demo of a text generation model trained with GPT-2 
+''')
+max_len = st.sidebar.slider(label='Output Size', min_value=1, max_value=150, value=10, step=1)
+# samples = st.sidebar.slider(label='Number of Samples', min_value=1, max_value=50, value=10, step=1)
+temp = st.sidebar.slider(label='Temperature', min_value=0.0, max_value=2.0, value=0.8, step=0.1)
+# temp = st.sidebar.slider(label='Temperature', min_value=0.1, max_value=1.0, value=5.0, step=0.05)
+# do_sample=st.sidebar.checkbox("do_sample")
+
+
+
+# max_len=st.slider("max_len",1,100,None,1,key="max_len")
+# top_k=st.slider("top_k",1,50,None,1)
+# do_sample=st.checkbox("do_sample")
+# print(max_len)
+sentence = st.text_area('Input your sentence here:') 
+clear=st.button("Clear")
+Enter=st.button("Generate")
+
+if clear:
+    print(clear)
+    st.markdown(' ')
+
+if Enter:
+    st.header("Output-")
+    print("Generating predictions......\n\n")
+    # out=generate(sentence,max_len,top_k,do_sample)
+    out=predict_query(sentence,max_len,temp)
+    for i,out in enumerate(out):
+        st.markdown(f"Sugestion {i} :{out}")

requirements.txt

@@ -0,0 +1,3 @@
+torch=1.11.0
+transformers==4.19.2
+streamlit

test.ipynb

@@ -0,0 +1,179 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import transformers\n",
+    "from transformers import AutoTokenizer, AutoModelWithLMHead\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\transformers\\models\\auto\\modeling_auto.py:664: FutureWarning: The class `AutoModelWithLMHead` is deprecated and will be removed in a future version. Please use `AutoModelForCausalLM` for causal language models, `AutoModelForMaskedLM` for masked language models and `AutoModelForSeq2SeqLM` for encoder-decoder models.\n",
+      "  FutureWarning,\n"
+     ]
+    }
+   ],
+   "source": [
+    "# model= AutoModelWithLMHead.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "Can't get attribute 'NewGELUActivation' on <module 'transformers.activations' from 'c:\\\\Users\\\\ADMIN\\\\textifyai\\\\lib\\\\site-packages\\\\transformers\\\\activations.py'>",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_9168/1093822913.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Gpt_neo_Epoch_10_Loss_031_data_5000.pth\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmap_location\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'cpu'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36mload\u001b[1;34m(f, map_location, pickle_module, **pickle_load_args)\u001b[0m\n\u001b[0;32m    605\u001b[0m                     \u001b[0mopened_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mseek\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0morig_position\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    606\u001b[0m                     \u001b[1;32mreturn\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mjit\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 607\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0m_load\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_zipfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmap_location\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    608\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0m_legacy_load\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmap_location\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    609\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36m_load\u001b[1;34m(zip_file, map_location, pickle_module, pickle_file, **pickle_load_args)\u001b[0m\n\u001b[0;32m    880\u001b[0m     \u001b[0munpickler\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mUnpicklerWrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    881\u001b[0m     \u001b[0munpickler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpersistent_load\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpersistent_load\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 882\u001b[1;33m     \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0munpickler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    883\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    884\u001b[0m     \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_utils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate_loaded_sparse_tensors\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36mfind_class\u001b[1;34m(self, mod_name, name)\u001b[0m\n\u001b[0;32m    873\u001b[0m         \u001b[1;32mdef\u001b[0m \u001b[0mfind_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    874\u001b[0m             \u001b[0mmod_name\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mload_module_mapping\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmod_name\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 875\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    876\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    877\u001b[0m     \u001b[1;31m# Load the data (which may in turn use `persistent_load` to load tensors)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mAttributeError\u001b[0m: Can't get attribute 'NewGELUActivation' on <module 'transformers.activations' from 'c:\\\\Users\\\\ADMIN\\\\textifyai\\\\lib\\\\site-packages\\\\transformers\\\\activations.py'>"
+     ]
+    }
+   ],
+   "source": [
+    "model=torch.load(\"Gpt_neo_Epoch_10_Loss_031_data_5000.pth\",map_location=torch.device('cpu'))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def predict_query(input_sentence,max_len=40,temp=0.7):\n",
+    "    pred=[]\n",
+    "    seq=tokenizer(input_sentence,return_tensors='pt')['input_ids'].to(device)\n",
+    "    outputs=model.generate(seq,\n",
+    "                          max_length=max_len,\n",
+    "                          do_sample=True,\n",
+    "                          top_p=0.95,\n",
+    "                          #num_beams=5,\n",
+    "                          temperature=temp,\n",
+    "                          no_repeat_ngram_size=3,\n",
+    "                          num_return_sequences=5\n",
+    "                          ).to(device)\n",
+    "    for i,out in enumerate(outputs):\n",
+    "      out=tokenizer.decode(out, skip_special_tokens=True)\n",
+    "      idx=out.find(\"<|sep|>\")+7\n",
+    "      out=out[idx:]\n",
+    "      print(f\"Sugestion{i} :{out}\")\n",
+    "      pred.append(tokenizer.decode(out, skip_special_tokens=True))\n",
+    "    return pred\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4.11.3\n"
+     ]
+    }
+   ],
+   "source": [
+    "import transformers\n",
+    "\n",
+    "print(transformers.__version__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.8.2+cu111\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "\n",
+    "print(torch.__version__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'tensorflow'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_3544/763479854.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mtensorflow\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"tf.__version__\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__version__\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'tensorflow'"
+     ]
+    }
+   ],
+   "source": [
+    "import tensorflow as tf\n",
+    "\n",
+    "print(\"tf.__version__\", tf.__version__)"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "c2aedac36a10eb432fae2be3be58ef9112ca6433e61b95db4d37b1628d19a18a"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.7.7 64-bit ('textifyai': venv)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}