initialize

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import datasets
+
+humaneval_v_data = datasets.load_from_disk("humaneval_v_test_hf")
+st.set_page_config(layout="wide", page_title="HumanEval-V Viewer")
+st.markdown("---")
+
+max_index = 108
+
+# Initialize session state for index if not present
+if 'index' not in st.session_state:
+    st.session_state.index = 1
+
+buttons = st.columns([2, 1, 6])
+
+with buttons[1]:
+    # Number input for navigation
+    index_input = st.number_input(
+        f"Go to index (1-{max_index}):", 
+        min_value=1, 
+        max_value=108, 
+        value=st.session_state.index, 
+        key="index_input", 
+        help="Enter an index and jump to that index.",
+        step=1  # Increment by 1
+    )
+
+with buttons[0]:
+    st.markdown("# HumanEval-V Viewer")
+    
+
+# Check if the input differs from the current session state and update it
+if index_input != st.session_state.index:
+    st.session_state.index = index_input
+    st.experimental_rerun()
+
+
+coding_task = humaneval_v_data[st.session_state.index-1]
+qid = coding_task["qid"]
+image = coding_task["image"]
+function_signature = coding_task["function_signature"]
+ground_truth = coding_task["ground_truth_solution"]
+test_script = coding_task["test_script"]
+
+upper_columns = st.columns([2, 7])
+with upper_columns[0]:
+    st.markdown(f"### Question ID: {qid}")
+    st.image(image, use_column_width=True)
+    st.markdown("---")
+with upper_columns[1]:
+    st.markdown(f"### Function Signature:")
+    st.markdown(f"")
+    st.markdown(f"""```python
+{function_signature}
+```""")
+    st.markdown(f"### Test Script:")
+    st.markdown(f"")
+    st.markdown(f"""```python
+{test_script}
+```""")
+    st.markdown(f"### Ground Truth Solution:")
+    st.markdown(f"")
+    st.markdown(f"""```python
+{ground_truth}
+```""")

humaneval_v_test_hf/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:774e4cacfc259917fb5a5e8433e6cacbcac01063cb30fd3560170b3a0a9fa76e
+size 12842912

humaneval_v_test_hf/dataset_info.json

@@ -0,0 +1,57 @@
+{
+  "builder_name": "parquet",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "human_eval-v-benchmark",
+  "dataset_size": 12841384,
+  "description": "",
+  "download_checksums": {
+    "hf://datasets/HumanEval-V/HumanEval-V-Benchmark@50af2be232641ca618f6aecce901ca5e5a83b20e/data/test-00000-of-00001.parquet": {
+      "num_bytes": 12571814,
+      "checksum": null
+    }
+  },
+  "download_size": 12571814,
+  "features": {
+    "qid": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "ground_truth_solution": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "image_description": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "test_script": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "function_signature": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "image": {
+      "_type": "Image"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 25413198,
+  "splits": {
+    "test": {
+      "name": "test",
+      "num_bytes": 12841384,
+      "num_examples": 108,
+      "dataset_name": "human_eval-v-benchmark"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

humaneval_v_test_hf/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "d8ffc8935ede93f4",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "test"
+}