feat: text ux

Dockerfile

@@ -1,5 +1,6 @@
-FROM python:3.9-slim
+FROM python:3.11-slim
 
+RUN pip3 install poetry=2.1.3
 WORKDIR /app
 
 RUN apt-get update && apt-get install -y \
@@ -9,10 +10,12 @@ RUN apt-get update && apt-get install -y \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-COPY requirements.txt ./
 COPY src/ ./src/
 
-RUN pip3 install -r requirements.txt
+# COPY requirements.txt ./
+# RUN pip3 install -r requirements.txt
+COPY pyproject.toml poetry.lock /app
+RUN poetry install
 
 EXPOSE 8501
 

pyproject.toml

@@ -0,0 +1,22 @@
+[project]
+name = "sft"
+version = "0.1.0"
+description = ""
+authors =  [
+    { name = "yongkyucho", email = "choco@conoz.net" },
+]
+license = "MIT"
+readme = "README.md"
+
+[build-system]
+requires = ["poetry-core>=2.0.0,<3.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.dependencies]
+python = "~3.11"
+
+torch = "2.7.0"
+sentence-transformers = "^3.0.0"
+
+streamlit = "^1.46.1"
+# unsloth = "^2025.6.8"

requirements.txt

@@ -1,3 +1,5 @@
 altair
 pandas
-streamlit
+streamlit
+transformers
+torch

src/streamlit_app.py

@@ -1,40 +1,79 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import torch
+from transformers import pipeline
+# from unsloth import FastLanguageModel, is_bfloat16_supported
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+
+def main():
+    st.title('Text Generator')
+    query = st.text_input('input your topic of interest')
+
+    alpaca_template = """Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+    ### Instruction:
+    {}
+
+    ### Response:
+    {}
+    """
+
+    # model_id = "sentence-transformers/all-MiniLM-L6-v2"
+    # model_id = "sentence-transformers/xlm-r-base-en-ko-nli-ststb"
+
+    # model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+    model_id = "meta-llama/Llama-3.2-1B"
+    # model_id="choco-conoz/TwinLlama-3.1-8B"
+    processor = pipeline(
+        "text-generation",
+        model=model_id,
+        model_kwargs={
+            "torch_dtype": torch.float16,
+            "quantization_config": {"load_in_4bit": True},
+            "low_cpu_mem_usage": True,
+        },
+    )
+    terminators = [
+        processor.tokenizer.eos_token_id,
+        processor.tokenizer.convert_tokens_to_ids(""),
+    ]
+
+    if st.button("Send"):
+        user_prompt = alpaca_template.format(query, "")
+        print('user_prompt', user_prompt)
+        prompt = processor.tokenizer.apply_chat_template(
+            user_prompt, tokenize=False, add_generation_prompt=True)
+        outputs = processor(prompt, max_new_tokens=4096, eos_token_id=terminators, do_sample=True,
+                            temperature=0.6, top_p=0.9
+                            )
+        response = outputs[0]["generated_text"][len(prompt):]
+        st.write(response)
+
+
+if __name__ == "__main__":
+    main()
+# >>> old
+# num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
+# num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+
+# indices = np.linspace(0, 1, num_points)
+# theta = 2 * np.pi * num_turns * indices
+# radius = indices
+
+# x = radius * np.cos(theta)
+# y = radius * np.sin(theta)
+
+# df = pd.DataFrame({
+#     "x": x,
+#     "y": y,
+#     "idx": indices,
+#     "rand": np.random.randn(num_points),
+# })
+
+# st.altair_chart(alt.Chart(df, height=700, width=700)
+#     .mark_point(filled=True)
+#     .encode(
+#         x=alt.X("x", axis=None),
+#         y=alt.Y("y", axis=None),
+#         color=alt.Color("idx", legend=None, scale=alt.Scale()),
+#         size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
+#     ))