update docs

app.py

@@ -101,14 +101,12 @@ with gr.Blocks(title=title) as demo:
     param_loss=" \
     2. `loss`: The loss function used for training. \
         The default is `squared_hinge`, which is a variant \
-        of hinge loss. Other options include `hinge` \
-        each with different properties and performance characteristics."
+        of hinge loss. The combination of penalty='l1' and \
+        loss='hinge' is not supported."
     param_penalty="\
     3. `penalty`: The type of regularization penalty \
         applied to the model. The default is `l2`, which uses \
-        the L2 norm. Other options include `l1` and \
-        which use the L1 norm and a combination of L1 and L2 norms, \
-        respectively."
+        the L2 norm."
     param_dual="\
     4. `dual`: Determines whether the dual or primal optimization \
         problem is solved. By default, `dual=True` when the number \
@@ -121,13 +119,15 @@ with gr.Blocks(title=title) as demo:
         a specified tolerance level."
     param_max_iter="\
     6. `max_iter`: The maximum number of iterations for solver \
-        convergence. If not specified, the default value is set."
+        convergence. If not specified, the default value is 1000."
     gr.Markdown(param_C)
     gr.Markdown(param_loss)
     gr.Markdown(param_penalty)
     gr.Markdown(param_dual)
     gr.Markdown(param_tol)
     gr.Markdown(param_max_iter)
+    gr.Markdown("Read more in the \
+    [original example](https://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html#sklearn.svm.LinearSVC).")
 
     
     n_samples = gr.Slider(minimum=20, maximum=100, step=5,