Duplicate from akhaliq/kogpt

Co-authored-by: Ahsen Khaliq <akhaliq@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+title: Kogpt
+emoji: 🌍
+colorFrom: red
+colorTo: gray
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: akhaliq/kogpt
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM 
+
+
+tokenizer = AutoTokenizer.from_pretrained(
+  'kakaobrain/kogpt', revision='KoGPT6B-ryan1.5b',
+  bos_token='[BOS]', eos_token='[EOS]', unk_token='[UNK]', pad_token='[PAD]', mask_token='[MASK]'
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+  'kakaobrain/kogpt', revision='KoGPT6B-ryan1.5b',
+  pad_token_id=tokenizer.eos_token_id,
+  torch_dtype=torch.float16, low_cpu_mem_usage=True
+).to(device='cpu', non_blocking=True)
+_ = model.eval()
+
+title = "KoGPT"
+description = "Gradio demo for KoGPT(Korean Generative Pre-trained Transformer). To use it, simply add your text, or click one of the examples to load them. Read more at the links below."
+article = "<p style='text-align: center'><a href='https://github.com/kakaobrain/kogpt' target='_blank'>KoGPT: KakaoBrain Korean(hangul) Generative Pre-trained Transformer</a> | <a href='https://huggingface.co/kakaobrain/kogpt' target='_blank'>Huggingface Model</a></p>"
+examples=[['인간처럼 생각하고, 행동하는 \'지능\'을 통해 인류가 이제까지 풀지 못했던']]
+def greet(text):
+    prompt = text
+    with torch.no_grad():
+      tokens = tokenizer.encode(prompt, return_tensors='pt').to(device='cpu', non_blocking=True)
+      gen_tokens = model.generate(tokens, do_sample=True, temperature=0.8, max_length=64)
+      generated = tokenizer.batch_decode(gen_tokens)[0]
+      
+    return generated
+    
+iface = gr.Interface(fn=greet, inputs="text", outputs="text", title=title, description=description, article=article, examples=examples,enable_queue=True)
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+sentencepiece
+torch