Duplicate from lcw99/gpt-neo-1.3B-ko-text-generator

Co-authored-by: Chang W Lee <lcw99@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,13 @@
+---
+title: Gpt Neo 1.3B Ko Text Generator
+emoji: 📉
+colorFrom: blue
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.10.0
+app_file: app.py
+pinned: false
+duplicated_from: lcw99/gpt-neo-1.3B-ko-text-generator
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,106 @@
+import copy
+
+import torch
+import torch.nn.functional as F
+from transformers import GPTNeoForCausalLM, AutoTokenizer, pipeline
+import numpy as np
+from tqdm import trange
+
+
+import streamlit as st
+
+
+def set_seed(seed):
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    try:
+        torch.cuda.manual_seed_all(seed)
+    except:
+        pass
+
+
+MODEL_CLASSES = {
+    'lcw99/gpt-neo-1.3B-ko-fp16': (GPTNeoForCausalLM, AutoTokenizer),
+    'lcw99/gpt-neo-1.3B-ko': (GPTNeoForCausalLM, AutoTokenizer),
+}
+
+
+# @st.cache
+def load_model(model_name):
+    model_class, tokenizer_class = MODEL_CLASSES[model_name]
+
+    model = model_class.from_pretrained(
+        model_name, 
+        torch_dtype=torch.float32,
+        low_cpu_mem_usage=True,
+        use_cache=False,
+        gradient_checkpointing=False,
+        device_map='auto',
+        #revision="float16",
+        #load_in_8bit=True
+    )
+    tokenizer = tokenizer_class.from_pretrained(model_name)
+
+    model.to(device)
+    model.eval()
+    return model, tokenizer
+
+
+if __name__ == "__main__":
+
+
+    # Selectors
+    model_name = st.sidebar.selectbox("Model", list(MODEL_CLASSES.keys()))
+    length = st.sidebar.slider("Length", 50, 2048, 100)
+    temperature = st.sidebar.slider("Temperature", 0.0, 3.0, 0.8)
+    top_k = st.sidebar.slider("Top K", 0, 10, 0)
+    top_p = st.sidebar.slider("Top P", 0.0, 1.0, 0.7)
+
+    st.title("Text generation with GPT-neo Korean")
+    raw_text = st.text_input("시작하는 문장을 입력하고 엔터를 치세요.", placeholder="골프를 잘 치고 싶다면,", 
+                             key="text_input1")
+
+    if raw_text:
+        st.write(raw_text)
+        with st.spinner(f'loading model({model_name}) wait...'):
+            device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+            model, tokenizer = load_model(model_name)
+
+            # making a copy so streamlit doesn't reload models
+            # model = copy.deepcopy(model)
+            # tokenizer = copy.deepcopy(tokenizer)
+
+            if False:
+                text_generation = pipeline(
+                    "text-generation",
+                    model=model,
+                    tokenizer=tokenizer,
+                )
+
+        with st.spinner(f'Generating text wait...'):        
+            # generated = text_generation(
+            #     raw_text,
+            #     max_length=length,
+            #     do_sample=True,
+            #     min_length=100,
+            #     num_return_sequences=3,
+            #     top_p=top_p,
+            #     top_k=top_k
+            # )
+            # st.write(*generated)
+            
+            encoded_input = tokenizer(raw_text, return_tensors='pt')
+            output_sequences = model.generate(
+                input_ids=encoded_input['input_ids'].to(device),
+                attention_mask=encoded_input['attention_mask'].to(device),
+                max_length=length,
+                do_sample=True,
+                min_length=20,
+                top_p=top_p,
+                top_k=top_k
+            )
+            generated = tokenizer.decode(output_sequences[0], skip_special_tokens=True)
+            #print(generated)
+            st.write(generated)
+            
+            

requirements.txt

@@ -0,0 +1,9 @@
+transformers
+numpy
+tqdm
+accelerate
+bitsandbytes==0.35.4
+--extra-index-url https://download.pytorch.org/whl/cu116
+torch
+torchvision 
+torchaudio