diff --git a/model/1.5.2/thai-ner-1-5-newmm-orchid.ipynb b/model/1.5.2/thai-ner-1-5-newmm-orchid.ipynb
new file mode 100644
index 0000000..01a0de4
--- /dev/null
+++ b/model/1.5.2/thai-ner-1-5-newmm-orchid.ipynb
@@ -0,0 +1,810 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install https://github.com/PyThaiNLP/pythainlp/archive/dev.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install nltk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_name=\"train\"\n",
+    "import codecs\n",
+    "from tqdm import tqdm\n",
+    "from pythainlp.tokenize import word_tokenize\n",
+    "from pythainlp.tag import pos_tag\n",
+    "from nltk.tokenize import RegexpTokenizer\n",
+    "import glob\n",
+    "import nltk\n",
+    "import re\n",
+    "# thai cut\n",
+    "thaicut=\"newmm\"\n",
+    "from sklearn.metrics import make_scorer\n",
+    "from sklearn.model_selection import cross_validate,train_test_split\n",
+    "import pycrfsuite\n",
+    "from pythainlp.corpus.common import thai_stopwords"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stopwords = list(thai_stopwords())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#จัดการประโยคซ้ำ\n",
+    "data_not=[]\n",
+    "def Unique(p):\n",
+    " text=re.sub(\"<[^>]*>\",\"\",p)\n",
+    " text=re.sub(\"\\[(.*?)\\]\",\"\",text)\n",
+    " text=re.sub(\"\\[\\/(.*?)\\]\",\"\",text)\n",
+    " if text not in data_not:\n",
+    "  data_not.append(text)\n",
+    "  return True\n",
+    " else:\n",
+    "  return False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# เตรียมตัวตัด tag ด้วย re\n",
+    "pattern = r'\\[(.*?)\\](.*?)\\[\\/(.*?)\\]'\n",
+    "tokenizer = RegexpTokenizer(pattern) # ใช้ nltk.tokenize.RegexpTokenizer เพื่อตัด [TIME]8.00[/TIME] ให้เป็น ('TIME','ไง','TIME')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# จัดการกับ tag ที่ไม่ได้ tag\n",
+    "def toolner_to_tag(text):\n",
+    " text=text.strip().replace(\"FACILITY\",\"LOCATION\").replace(\"[AGO]\",\"\").replace(\"[/AGO]\",\"\").replace(\"[T]\",\"\").replace(\"[/T]\",\"\")\n",
+    " text=re.sub(\"<[^>]*>\",\"\",text)\n",
+    " text=re.sub(\"(\\[\\/(.*?)\\])\",\"\\\\1***\",text)#.replace('(\\[(.*?)\\])','***\\\\1')# text.replace('>','>***') # ตัดการกับพวกไม่มี tag word\n",
+    " text=re.sub(\"(\\[\\w+\\])\",\"***\\\\1\",text)\n",
+    " text2=[]\n",
+    " for i in text.split('***'):\n",
+    "  if \"[\" in i:\n",
+    "   text2.append(i)\n",
+    "  else:\n",
+    "   text2.append(\"[word]\"+i+\"[/word]\")\n",
+    " text=\"\".join(text2)#re.sub(\"[word][/word]\",\"\",\"\".join(text2))\n",
+    " return text.replace(\"[word][/word]\",\"\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# แปลง text ให้เป็น conll2002\n",
+    "def text2conll2002(text,pos=True):\n",
+    "    \"\"\"\n",
+    "    ใช้แปลงข้อความให้กลายเป็น conll2002\n",
+    "    \"\"\"\n",
+    "    text=toolner_to_tag(text)\n",
+    "    text=text.replace(\"''\",'\"')\n",
+    "    text=text.replace(\"’\",'\"').replace(\"‘\",'\"')#.replace('\"',\"\")\n",
+    "    tag=tokenizer.tokenize(text)\n",
+    "    j=0\n",
+    "    conll2002=\"\"\n",
+    "    for tagopen,text,tagclose in tag:\n",
+    "        word_cut=word_tokenize(text,engine=thaicut) # ใช้ตัวตัดคำ newmm\n",
+    "        i=0\n",
+    "        txt5=\"\"\n",
+    "        while i<len(word_cut):\n",
+    "            if word_cut[i]==\"''\" or word_cut[i]=='\"':pass\n",
+    "            elif i==0 and tagopen!='word':\n",
+    "                txt5+=word_cut[i]\n",
+    "                txt5+='\\t'+'B-'+tagopen\n",
+    "            elif tagopen!='word':\n",
+    "                txt5+=word_cut[i]\n",
+    "                txt5+='\\t'+'I-'+tagopen\n",
+    "            else:\n",
+    "                txt5+=word_cut[i]\n",
+    "                txt5+='\\t'+'O'\n",
+    "            txt5+='\\n'\n",
+    "            #j+=1\n",
+    "            i+=1\n",
+    "        conll2002+=txt5\n",
+    "    if pos==False:\n",
+    "        return conll2002\n",
+    "    return postag(conll2002)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ใช้สำหรับกำกับ pos tag เพื่อใช้กับ NER\n",
+    "def postag(text):\n",
+    "    listtxt=[i for i in text.split('\\n') if i!='']\n",
+    "    list_word=[]\n",
+    "    for data in listtxt:\n",
+    "        list_word.append(data.split('\\t')[0])\n",
+    "    #print(text)\n",
+    "    list_word=pos_tag(list_word,engine=\"perceptron\", corpus=\"orchid\")\n",
+    "    text=\"\"\n",
+    "    i=0\n",
+    "    for data in listtxt:\n",
+    "        text+=data.split('\\t')[0]+'\\t'+list_word[i][1]+'\\t'+data.split('\\t')[1]+'\\n'\n",
+    "        i+=1\n",
+    "    return text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# เขียนไฟล์ข้อมูล conll2002\n",
+    "def write_conll2002(file_name,data):\n",
+    "    \"\"\"\n",
+    "    ใช้สำหรับเขียนไฟล์\n",
+    "    \"\"\"\n",
+    "    with codecs.open(file_name, \"w\", \"utf-8-sig\") as temp:\n",
+    "        temp.write(data)\n",
+    "    return True\n",
+    "# อ่านข้อมูลจากไฟล์\n",
+    "def get_data(fileopen):\n",
+    "\t\"\"\"\n",
+    "    สำหรับใช้อ่านทั้งหมดทั้งในไฟล์ทีละรรทัดออกมาเป็น list\n",
+    "    \"\"\"\n",
+    "\twith codecs.open(fileopen, 'r',encoding='utf-8-sig') as f:\n",
+    "\t\tlines = f.read().splitlines()\n",
+    "\treturn [a for a in tqdm(lines) if Unique(a)] # เอาไม่ซ้ำกัน"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def alldata(lists):\n",
+    "    text=\"\"\n",
+    "    for data in lists:\n",
+    "        text+=text2conll2002(data)\n",
+    "        text+='\\n'\n",
+    "    return text\n",
+    "\n",
+    "def alldata_list(lists):\n",
+    "    data_all=[]\n",
+    "    for data in lists:\n",
+    "        data_num=[]\n",
+    "        try:\n",
+    "            txt=text2conll2002(data,pos=True).split('\\n')\n",
+    "            for d in txt:\n",
+    "                tt=d.split('\\t')\n",
+    "                if d!=\"\":\n",
+    "                    if len(tt)==3:\n",
+    "                        data_num.append((tt[0],tt[1],tt[2]))\n",
+    "                    else:\n",
+    "                        data_num.append((tt[0],tt[1]))\n",
+    "            #print(data_num)\n",
+    "            data_all.append(data_num)\n",
+    "        except:\n",
+    "            print(data)\n",
+    "    #print(data_all)\n",
+    "    return data_all\n",
+    "\n",
+    "def alldata_list_str(lists):\n",
+    "\tstring=\"\"\n",
+    "\tfor data in lists:\n",
+    "\t\tstring1=\"\"\n",
+    "\t\tfor j in data:\n",
+    "\t\t\tstring1+=j[0]+\"\t\"+j[1]+\"\t\"+j[2]+\"\\n\"\n",
+    "\t\tstring1+=\"\\n\"\n",
+    "\t\tstring+=string1\n",
+    "\treturn string\n",
+    "\n",
+    "def get_data_tag(listd):\n",
+    "\tlist_all=[]\n",
+    "\tc=[]\n",
+    "\tfor i in listd:\n",
+    "\t\tif i !='':\n",
+    "\t\t\tc.append((i.split(\"\\t\")[0],i.split(\"\\t\")[1],i.split(\"\\t\")[2]))\n",
+    "\t\telse:\n",
+    "\t\t\tlist_all.append(c)\n",
+    "\t\t\tc=[]\n",
+    "\treturn list_all\n",
+    "def getall(lista):\n",
+    "    ll=[]\n",
+    "    for i in tqdm(lista):\n",
+    "        o=True\n",
+    "        for j in ll:\n",
+    "            if re.sub(\"\\[(.*?)\\]\",\"\",i)==re.sub(\"\\[(.*?)\\]\",\"\",j):\n",
+    "                o=False\n",
+    "                break\n",
+    "        if o==True:\n",
+    "            ll.append(i)\n",
+    "    return ll"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100% 5096/5096 [00:00<00:00, 19535.85it/s]\n",
+      "100% 5089/5089 [02:05<00:00, 40.40it/s] "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5089\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "data1=getall(get_data(file_name+\".txt\"))\n",
+    "print(len(data1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100% 510/510 [00:00<00:00, 10777.82it/s]\n",
+      "0it [00:00, ?it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "val=getall(get_data(\"val.txt\"))\n",
+    "print(len(val))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100% 1274/1274 [00:00<00:00, 11050.81it/s]\n",
+      "100% 1274/1274 [00:08<00:00, 158.35it/s]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1274\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "test=getall(get_data(\"test.txt\"))\n",
+    "print(len(test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data=alldata_list(data1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "val_data=alldata_list(val)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_data=alldata_list(test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5089\n",
+      "0\n",
+      "1274\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(train_data))\n",
+    "print(len(val_data))\n",
+    "print(len(test_data))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def isThai(chr):\n",
+    " cVal = ord(chr)\n",
+    " if(cVal >= 3584 and cVal <= 3711):\n",
+    "  return True\n",
+    " return False\n",
+    "def isThaiWord(word):\n",
+    " t=True\n",
+    " for i in word:\n",
+    "  l=isThai(i)\n",
+    "  if l!=True and i!='.':\n",
+    "   t=False\n",
+    "   break\n",
+    " return t\n",
+    "\n",
+    "def is_stopword(word):\n",
+    "    return word in stopwords\n",
+    "def is_s(word):\n",
+    "    if word == \" \" or word ==\"\\t\" or word==\"\":\n",
+    "        return True\n",
+    "    else:\n",
+    "        return False\n",
+    "\n",
+    "def lennum(word,num):\n",
+    "    if len(word)==num:\n",
+    "        return True\n",
+    "    return False\n",
+    "def doc2features(doc, i):\n",
+    "    word = doc[i][0]\n",
+    "    postag = doc[i][1]\n",
+    "    # Features from current word\n",
+    "    features={\n",
+    "        'word.word': word,\n",
+    "        'word.stopword': is_stopword(word),\n",
+    "        'word.isthai':isThaiWord(word),\n",
+    "        'word.isspace':word.isspace(),\n",
+    "        'postag':postag,\n",
+    "        'word.isdigit()': word.isdigit()\n",
+    "    }\n",
+    "    if word.isdigit() and len(word)==5:\n",
+    "        features['word.islen5']=True\n",
+    "    if i > 0:\n",
+    "        prevword = doc[i-1][0]\n",
+    "        postag1 = doc[i-1][1]\n",
+    "        features['word.prevword'] = prevword\n",
+    "        features['word.previsspace']=prevword.isspace()\n",
+    "        features['word.previsthai']=isThaiWord(prevword)\n",
+    "        features['word.prevstopword']=is_stopword(prevword)\n",
+    "        features['word.prepostag'] = postag1\n",
+    "        features['word.prevwordisdigit'] = prevword.isdigit()\n",
+    "    else:\n",
+    "        features['BOS'] = True # Special \"Beginning of Sequence\" tag\n",
+    "    # Features from next word\n",
+    "    if i < len(doc)-1:\n",
+    "        nextword = doc[i+1][0]\n",
+    "        postag1 = doc[i+1][1]\n",
+    "        features['word.nextword'] = nextword\n",
+    "        features['word.nextisspace']=nextword.isspace()\n",
+    "        features['word.nextpostag'] = postag1\n",
+    "        features['word.nextisthai']=isThaiWord(nextword)\n",
+    "        features['word.nextstopword']=is_stopword(nextword)\n",
+    "        features['word.nextwordisdigit'] = nextword.isdigit()\n",
+    "    else:\n",
+    "        features['EOS'] = True # Special \"End of Sequence\" tag\n",
+    "    return features\n",
+    "\n",
+    "def extract_features(doc):\n",
+    "    return [doc2features(doc, i) for i in range(len(doc))]\n",
+    "\n",
+    "def get_labels(doc):\n",
+    "    return [tag for (token,postag,tag) in doc]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100% 5089/5089 [00:08<00:00, 581.88it/s] \n",
+      "100% 5089/5089 [00:00<00:00, 113477.69it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "X_data = [extract_features(doc) for doc in tqdm(train_data)]\n",
+    "y_data = [get_labels(doc) for doc in tqdm(train_data)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3.03 s, sys: 35.9 ms, total: 3.07 s\n",
+      "Wall time: 3.07 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "trainer = pycrfsuite.Trainer(verbose=False)\n",
+    "i=0\n",
+    "for xseq, yseq in zip(X_data, y_data):\n",
+    "    try:\n",
+    "      trainer.append(xseq, yseq)\n",
+    "      i+=1\n",
+    "    except:\n",
+    "      pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "trainer.set_params({\n",
+    "    'c1': 0.1,   # coefficient for L1 penalty\n",
+    "    'c2': 0.1,  # coefficient for L2 penalty\n",
+    "    'max_iterations': 500,  # stop earlier\n",
+    "\n",
+    "    # include transitions that are possible, but not observed\n",
+    "    'feature.possible_transitions': True\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['feature.minfreq',\n",
+       " 'feature.possible_states',\n",
+       " 'feature.possible_transitions',\n",
+       " 'c1',\n",
+       " 'c2',\n",
+       " 'max_iterations',\n",
+       " 'num_memories',\n",
+       " 'epsilon',\n",
+       " 'period',\n",
+       " 'delta',\n",
+       " 'linesearch',\n",
+       " 'max_linesearch']"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "trainer.params()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 11min 51s, sys: 290 ms, total: 11min 51s\n",
+      "Wall time: 11min 51s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "trainer.train('thai-ner-1-5-newmm-orchid.crfsuite')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100% 1274/1274 [00:02<00:00, 597.40it/s]\n",
+      "100% 1274/1274 [00:00<00:00, 161749.10it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "X_test = [extract_features(doc) for doc in tqdm(test_data)]\n",
+    "y_test = [get_labels(doc) for doc in tqdm(test_data)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import LabelBinarizer\n",
+    "from itertools import chain\n",
+    "from sklearn.metrics import classification_report\n",
+    "def bio_classification_report(y_true, y_pred):\n",
+    "    \"\"\"\n",
+    "    Classification report for a list of BIO-encoded sequences.\n",
+    "    It computes token-level metrics and discards \"O\" labels.\n",
+    "    \n",
+    "    Note that it requires scikit-learn 0.15+ (or a version from github master)\n",
+    "    to calculate averages properly!\n",
+    "    \"\"\"\n",
+    "    lb = LabelBinarizer()\n",
+    "    y_true_combined = lb.fit_transform(list(chain.from_iterable(y_true)))\n",
+    "    y_pred_combined = lb.transform(list(chain.from_iterable(y_pred)))\n",
+    "        \n",
+    "    tagset = set(lb.classes_) - {'O'}\n",
+    "    tagset = sorted(tagset, key=lambda tag: tag.split('-', 1)[::-1])\n",
+    "    class_indices = {cls: idx for idx, cls in enumerate(lb.classes_)}\n",
+    "    \n",
+    "    return classification_report(\n",
+    "        y_true_combined,\n",
+    "        y_pred_combined,\n",
+    "        labels = [class_indices[cls] for cls in tagset],\n",
+    "        target_names = tagset,\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<contextlib.closing at 0x7fb3a9158be0>"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tagger = pycrfsuite.Tagger()\n",
+    "tagger.open('thai-ner-1-5-newmm-orchid.crfsuite')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = list(tagger.info().labels.keys())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels.remove('O')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import f1_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 746 ms, sys: 4.02 ms, total: 750 ms\n",
+      "Wall time: 749 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "y_pred = [tagger.tag(xseq) for xseq in X_test]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = list(tagger.info().labels.keys())\n",
+    "labels.remove('O')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                precision    recall  f1-score   support\n",
+      "\n",
+      "        B-DATE       0.93      0.83      0.87       350\n",
+      "        I-DATE       0.94      0.93      0.93       665\n",
+      "         B-LAW       0.88      0.53      0.66        87\n",
+      "         I-LAW       0.88      0.64      0.74       253\n",
+      "         B-LEN       1.00      0.75      0.86        12\n",
+      "         I-LEN       1.00      0.69      0.82        26\n",
+      "    B-LOCATION       0.81      0.69      0.75       620\n",
+      "    I-LOCATION       0.75      0.68      0.71       533\n",
+      "       B-MONEY       0.99      0.88      0.93       131\n",
+      "       I-MONEY       0.98      0.93      0.95       321\n",
+      "B-ORGANIZATION       0.91      0.69      0.79      1334\n",
+      "I-ORGANIZATION       0.79      0.72      0.75      1198\n",
+      "     B-PERCENT       0.88      0.88      0.88        17\n",
+      "     I-PERCENT       0.88      0.95      0.91        22\n",
+      "      B-PERSON       0.95      0.77      0.85       607\n",
+      "      I-PERSON       0.93      0.88      0.91      2181\n",
+      "       B-PHONE       1.00      0.50      0.67         2\n",
+      "       I-PHONE       1.00      1.00      1.00         8\n",
+      "        B-TIME       0.93      0.64      0.76        87\n",
+      "        I-TIME       0.94      0.76      0.84       158\n",
+      "         B-URL       0.91      0.83      0.87        12\n",
+      "         I-URL       0.93      0.96      0.94        94\n",
+      "\n",
+      "     micro avg       0.89      0.79      0.84      8718\n",
+      "     macro avg       0.92      0.78      0.84      8718\n",
+      "  weighted avg       0.89      0.79      0.83      8718\n",
+      "   samples avg       0.16      0.16      0.16      8718\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1308: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in samples with no predicted labels. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, msg_start, len(result))\n",
+      "/opt/conda/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1308: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in samples with no true labels. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, msg_start, len(result))\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(bio_classification_report(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!mv thai-ner-1-5-newmm-orchid.crfsuite thainer_crf_1_5_2.model"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/model/1.5.2/thainer_crf_1_5_2.model b/model/1.5.2/thainer_crf_1_5_2.model
new file mode 100644
index 0000000..c7a846e
Binary files /dev/null and b/model/1.5.2/thainer_crf_1_5_2.model differ