Add application file

.gitignore

@@ -0,0 +1 @@
+/env

Intro.py

@@ -0,0 +1,34 @@
+import os
+import streamlit as st
+
+st.title("Intro")
+
+st.write("")
+st.write("")
+
+st.subheader("Available Models")
+st.markdown(
+    "Random Model -  generates the name randomly"
+)
+st.markdown(
+    "Bigram model -  character level model, 2 character understanding"
+)
+
+st.markdown(
+            "[repo link](https://github.com/SDcodehub/make_over.git)"
+)
+
+st.markdown(
+            "[Dataset](https://github.com/SDcodehub/make_over/blob/main/data/names.txt)"
+)
+
+
+st.subheader("Ref")
+st.markdown(
+    "https://youtu.be/PaCmpygFfXo?si=MjyUM2oBykhJNuy1"
+)
+
+st.subheader("Credit to")
+st.markdown(
+    "Andrej Karpathy"
+)

README.md

@@ -1,13 +1,10 @@
----
-title: Make Over
-emoji: 🦀
-colorFrom: red
-colorTo: yellow
-sdk: streamlit
-sdk_version: 1.25.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# make_over
+
+Available Models
+
+	Random Model -  generates the name randomly
+	Bigram model -  character level model, 2 character understanding
+
+Ref - https://youtu.be/PaCmpygFfXo?si=MjyUM2oBykhJNuy1
+
+Credit to - Andrej Karpathy

models/bigram-USA.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fd93e301e5d453f7afe0306907a083174608c4ad104b539d8381b8ce738570
+size 3636

network/example_gen.py

@@ -0,0 +1,2 @@
+import torch
+

network/network.py

@@ -0,0 +1,97 @@
+import os
+from pathlib import Path
+import string
+import torch
+import torch.nn.functional as F
+
+
+class NeuralNetwork:
+    def __init__(self, lr, manual_seed) -> None:
+
+        self.lr = lr
+        chars = list(string.ascii_lowercase)
+        chars.insert(0, '.')
+        # string to index mapping we will call it as stoi
+        self.stoi = {s:i for i,s in enumerate(chars)}
+        self.itos = {i:s for s,i in self.stoi.items()}
+
+        # For character level model, 26 character and +1 for start and end special character
+        self.num_classes=27
+
+        self.g = torch.Generator().manual_seed(manual_seed)
+
+    def initialise_weights(self):
+        # initialise the 'network'
+        w = torch.randn((27,27), generator=self.g, requires_grad=True)
+        return w
+
+    def forward_pass(self, xs, w):
+        # forward pass
+        xenc = F.one_hot(xs, num_classes=self.num_classes).float() # input to the network one hot encodding
+        logits = xenc @ w
+        counts = logits.exp()
+        probs = counts / counts.sum(1, keepdims=True)
+        return probs
+
+    def loss(self, probs, ys, num):
+
+        loss = -probs[torch.arange(num), ys].log().mean()
+        print(f'{loss.item()=}')
+        return loss
+    
+    def backword_pass(self, loss, w):
+        # backward pass
+        w.grad = None
+        loss.backward()
+    
+    def update_weights(self,w):
+        # update
+        w.data += -self.lr * w.grad
+
+    def example_gen(self, words):
+        xs, ys = [], []
+        for w in words:
+            chs = '.' + w+ '.'
+            for ch1, ch2 in zip(chs, chs[1:]):
+                ix1 = self.stoi[ch1]
+                ix2 = self.stoi[ch2]
+                xs.append(ix1)
+                ys.append(ix2)
+        xs = torch.tensor(xs)
+        ys = torch.tensor(ys)
+        num=xs.nelement()
+        print(f'number of eaxmples: {num}')
+        return xs, ys, num
+
+
+if __name__ == '__main__':
+
+    get_cwd = os.getcwd()
+    project_dir = Path(get_cwd).parents[0]
+    data_path = os.path.join(project_dir, 'data')
+    words = open(os.path.join(data_path, "names.txt"), 'r').read().splitlines()
+
+    nn = NeuralNetwork(1,2147483647)
+
+    # Gen examples
+    xs, ys, num = nn.example_gen(words)
+
+    w = nn.initialise_weights()
+
+
+    for k in range(500):
+
+        # forward pass
+        probs = nn.forward_pass(xs,w)
+
+        # loss
+        loss = nn.loss(probs, ys, num)
+
+        # backward pass
+        nn.backword_pass(loss, w)
+
+        #update
+        nn.update_weights(w)
+
+
+

notebook/bigram-USA.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fd93e301e5d453f7afe0306907a083174608c4ad104b539d8381b8ce738570
+size 3636

pages/Name_Generator.py

@@ -0,0 +1,59 @@
+import os
+from pathlib import Path
+import streamlit as st
+import torch 
+from network.network import NeuralNetwork
+import torch.nn.functional as F
+
+# Page title
+st.set_page_config(page_title='Name Generator')
+st.title('Name Generator')
+
+# Select Model - drop down
+model_list = [
+    'Random model',
+  'Bigram model'
+]
+model_name = st.selectbox('Select an example query:', model_list)
+
+# Number of outputs - input field
+num_results = st.number_input("Number of Names to be Generated", min_value=1, max_value=50) 
+
+# Process
+# get weights
+with st.form('myform', clear_on_submit=True):
+
+    submitted = st.form_submit_button('Submit')
+
+    if submitted:
+        # get current path
+        get_cwd = os.getcwd()
+        project_dir = get_cwd
+        models_path = os.path.join(project_dir, 'models')
+
+        if model_name == 'Bigram model':
+            w = torch.load(os.path.join(models_path, 'bigram-USA.pt'))
+        elif model_name == 'Random model':
+            w = torch.ones(27,27) * 0.01
+
+        for i in range(num_results):
+            ix = 0
+            name=""
+            y = torch.Generator().manual_seed(2147483647)
+            while True:
+                nn = NeuralNetwork(50, 2147483647)
+
+                xenc = F.one_hot(torch.tensor([ix]), num_classes=27).float() # input to the network one hot encodding
+                logits = xenc @ w
+                counts = logits.exp()
+                probs = counts / counts.sum(1, keepdims=True)
+
+                ix = torch.multinomial(probs, num_samples=1, replacement=True).item()
+                name += nn.itos[ix]
+                if nn.itos[ix] ==".":
+                    break
+            st.write(name)
+
+
+
+

requirements.txt

@@ -0,0 +1,84 @@
+altair==5.0.1
+asttokens==2.2.1
+attrs==23.1.0
+backcall==0.2.0
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+colorama==0.4.6
+comm==0.1.4
+contourpy==1.1.0
+cycler==0.11.0
+debugpy==1.6.7.post1
+decorator==5.1.1
+executing==1.2.0
+filelock==3.12.2
+fonttools==4.42.0
+gitdb==4.0.10
+GitPython==3.1.32
+idna==3.4
+importlib-metadata==6.8.0
+ipykernel==6.25.1
+ipython==8.14.0
+jedi==0.19.0
+Jinja2==3.1.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+jupyter_client==8.3.0
+jupyter_core==5.3.1
+kiwisolver==1.4.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mpmath==1.3.0
+nest-asyncio==1.5.7
+networkx==3.1
+numpy==1.25.2
+packaging==23.1
+pandas==2.0.3
+parso==0.8.3
+pickleshare==0.7.5
+Pillow==9.5.0
+platformdirs==3.10.0
+prompt-toolkit==3.0.39
+protobuf==4.24.0
+psutil==5.9.5
+pure-eval==0.2.2
+pyarrow==12.0.1
+pydeck==0.8.0
+Pygments==2.16.1
+Pympler==1.0.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+pywin32==306
+pyzmq==25.1.1
+referencing==0.30.2
+requests==2.31.0
+rich==13.5.2
+rpds-py==0.9.2
+six==1.16.0
+smmap==5.0.0
+stack-data==0.6.2
+streamlit==1.25.0
+sympy==1.12
+tenacity==8.2.3
+toml==0.10.2
+toolz==0.12.0
+torch==2.0.1
+torchvision==0.15.2
+tornado==6.3.3
+traitlets==5.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.4
+validators==0.21.2
+watchdog==3.0.0
+wcwidth==0.2.6
+zipp==3.16.2