Add files from previous repo

.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

.gitignore

@@ -0,0 +1 @@
+__pycache__/

README.md

@@ -0,0 +1,14 @@
+---
+title: Topic Labelling Playground
+emoji: 🚀
+colorFrom: green
+colorTo: green
+sdk: streamlit
+sdk_version: 1.27.2
+app_file: app.py
+pinned: false
+license: other
+models:
+- textminr/llama-2-7b-4bit-gptq
+- textminr/llama-2-7b-chat-4bit-gptq
+---

app.py

@@ -0,0 +1,91 @@
+from huggingface_hub import list_models
+import streamlit as st
+from model import ReplicateModel
+
+import os
+import pandas as pd
+
+DATASETS_PATH = 'datasets'
+
+models = {
+  'mistral': ReplicateModel('mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70'),
+}
+
+prompts = {
+  'simple_prompt':
+    '''
+    I have topic that is described by the following keywords: [KEYWORDS]
+
+    Based on the information above, extract a short topic label in the following format:
+    topic: <topic label>
+    '''
+  # 'custom_prompt': ''
+}
+
+topicsets = {
+  'lda_poe_topics': os.path.join(DATASETS_PATH, 'lda_poe_topics.csv'),
+}
+
+@st.cache_data(show_spinner=False)
+def get_available_models():
+  # return [model.modelId for model in list_models(author='textminr')]
+  return models.keys()
+
+@st.cache_resource(show_spinner='Loading model...')
+def load_model(model_name: str):
+  # model = AutoGPTQForCausalLM.from_quantized(model_name, device_map='auto')
+  # return pipeline('text-generation', model=model, tokenizer=model_name)
+  return models[model_name].load()
+
+st.set_page_config(page_title='TL playground', page_icon='🚀', layout='wide')
+st.title('🚀 Topic Labelling playground')
+
+percentage_width_main = 70
+st.markdown(
+    f'''<style>
+    @media only screen and (min-width: 1500px) {{
+      .appview-container .main .block-container{{
+        max-width: {percentage_width_main}%;
+      }}
+    }}
+    </style>
+    ''',
+    unsafe_allow_html=True,
+)
+
+col1, col2 = st.columns(2, gap='medium')
+
+sel_model_name = col1.selectbox('Select a model', models, index=None, placeholder='Select a model')
+if sel_model_name:
+  model = load_model(sel_model_name)
+
+sel_dataset_name = col1.selectbox('Select a dataset', topicsets.keys(), index=None)
+if sel_dataset_name:
+  sel_dataset = pd.read_csv(topicsets[sel_dataset_name], header=None)
+  col1.dataframe(sel_dataset)
+
+  sel_row_index = col1.selectbox('Select a row', sel_dataset.index)
+
+sel_prompt = col2.selectbox('Select a prompt', prompts.keys())
+if sel_prompt != 'custom_prompt':
+  col2.code(prompts[sel_prompt], language='text')
+  sel_prompt_text = prompts[sel_prompt]
+else:
+  sel_prompt_text = st.text_area('Custom prompt', height=200)
+  col2.caption('Make sure to use "[KEYWORDS]" to indicate where the keywords should be inserted.')
+
+btn_generate = col2.button('Generate', disabled=(sel_model_name is None or sel_dataset_name is None))
+if btn_generate:
+  keywords = ','.join(sel_dataset.iloc[sel_row_index].tolist()[1:])
+
+  placeholder = col2.empty()
+  with placeholder, st.spinner('Generating...'):
+    prompt = sel_prompt_text.replace('[KEYWORDS]', keywords)
+    # result = model(prompt, max_new_tokens=100, return_full_text=False)[0]['generated_text']
+    result = model.generate(prompt)
+
+  message = col2.chat_message("ai")
+  message.write(result)
+  message.caption('Keywords: ' + keywords)
+
+  

datasets/lda_poe_topics.csv

@@ -0,0 +1,40 @@
+Topic 1,howev,even,found,period,altogeth,imposs,precis,perhap,short,prove
+Topic 2,water,wind,black,vessel,larg,sea,river,white,heavi,float
+Topic 3,beauti,shall,name,whose,new,tree,angel,find,flower,fair
+Topic 4,will,say,mean,rememb,speak,know,none,jupit,dare,limb
+Topic 5,call,may,doubt,matter,question,exist,mind,beyond,term,now
+Topic 6,one,everi,thing,moment,just,instant,anoth,almost,inde,frame
+Topic 7,point,must,certain,fact,case,view,captain,given,consid,import
+Topic 8,immedi,found,near,saw,state,now,present,sever,discov,approach
+Topic 9,made,make,way,attempt,get,forc,difficulti,account,escap,effort
+Topic 10,two,three,feet,year,hour,half,four,minut,thousand,hundr
+Topic 11,whole,form,earth,small,around,figur,stood,portion,surfac,vast
+Topic 12,upon,eye,look,fell,face,floor,fall,spot,depend,tabl
+Topic 13,one,hope,power,leav,follow,entir,scarc,consider,pass,mad
+Topic 14,man,old,die,away,live,ladi,young,busi,gentleman,pass
+Topic 15,time,first,long,second,keep,thought,circumst,instanc,letter,care
+Topic 16,much,evid,gave,although,truth,express,mean,seem,sens,felt
+Topic 17,like,light,ever,life,dream,dark,moon,wild,deep,appear
+Topic 18,effect,appear,step,upon,except,found,caus,event,discov,produc
+Topic 19,day,night,last,long,continu,cours,late,arriv,bring,raven
+Topic 20,lie,side,full,went,length,peter,augustus,lay,deck,board
+Topic 21,far,air,seem,heaven,high,sun,breath,grew,atmospher,rise
+Topic 22,now,becam,soon,distinct,object,absolut,necessari,appar,render,felt
+Topic 23,poem,poe,origin,work,first,read,poet,note,paper,line
+Topic 24,great,degre,island,sea,reach,set,land,strong,measur,sight
+Topic 25,natur,feel,excit,interest,true,differ,intens,result,principl,peculiar
+Topic 26,less,part,appear,thus,regard,posit,person,number,greater,mention
+Topic 27,hand,left,place,take,took,right,arm,hold,put,end
+Topic 28,without,bodi,reason,believ,suppos,corps,becom,madam,murder,least
+Topic 29,still,idea,think,fanci,human,dead,possess,impress,smile,wonder
+Topic 30,death,voic,sound,bell,heard,ear,low,without,fire,proceed
+Topic 31,word,let,thus,attent,utter,spoke,alon,gone,repeat,scene
+Topic 32,head,turn,came,upon,back,extrem,sudden,come,near,round
+Topic 33,mani,manner,charact,particular,subject,singular,success,weather,alway,articl
+Topic 34,littl,mere,remain,purpos,better,longer,suffer,use,wish,home
+Topic 35,now,thou,friend,sure,inde,say,repli,art,fear,sir
+Topic 36,well,good,among,observ,world,general,known,men,may,knew
+Topic 37,said,might,possibl,thought,taken,king,still,bird,yes,dupin
+Topic 38,open,door,within,close,room,chamber,wall,enter,main,box
+Topic 39,never,can,noth,see,yet,seen,even,done,know,eye
+Topic 40,love,thi,heart,soul,spirit,thee,god,shadow,within,passion

model.py

@@ -0,0 +1,25 @@
+from abc import ABC, abstractmethod
+import replicate
+
+class GenericModel:
+  def __init__(self, name: str):
+    self.name = name
+
+  @abstractmethod
+  def load(self):
+    pass
+
+  @abstractmethod
+  def generate(self, prompt: str):
+    pass
+
+class ReplicateModel(GenericModel):
+  def __init__(self, name: str):
+    super().__init__(name)
+
+  def load(self):
+    return self
+
+  def generate(self, prompt: str):
+    iterator = replicate.run(self.name, input={'prompt': prompt})
+    return ''.join(item for item in iterator)

requirements.txt

@@ -0,0 +1,3 @@
+transformers @ git+https://github.com/huggingface/transformers
+replicate
+auto_gptq