GZUzxc
/

TaskDialogVis_Model

@@ -1,14 +1,14 @@
----
-license: apache-2.0
-datasets:
-- GZUzxc/TaskDialogData
-language:
-- en
-metrics:
-- bleu
-base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
----
 ---
 # Model Card for TaskDialogViz
@@ -81,19 +81,26 @@ model = AutoModelForSeq2SeqLM.from_pretrained("GZUzxc/TaskDialogVis_Model", devi
 # Example input: Simulating the second turn of a dialogue.
 # The first turn has already generated a bar chart comparing the average sales of different stores.
-input_text = (
-    "<head> <field> Store, Weekly_Sales, Holiday_Flag, Unemployment, CPI </field> <type> nominal, quantitative, nominal, quantitative, quantitative </type> </head>"
-    "<data> <line 1> 1, 164369, 0, 8.106, 211.28919 </line 1> <line 2> 2, 164195, 1, 7.787, 215.61247 </line 2> </data>"
-    "<previous utterance> Compare the average sales of different stores? </previous utterance>"
-    "<previous chart> {'mark': 'bar', 'encoding': {'x': {'field': 'Store'}, 'y': {'field': 'Weekly_Sales', 'aggregate': 'mean'}}} </previous chart>"
-    "<utterance> Which stores have higher average sales? </utterance>"
-)
-# Goal: Perform the first step of reasoning.
-# Note: In actual use, the prompt for each step is fixed. This is simplified for demonstration purposes.
-prompt_for_step1 = f"{input_text} <step 1> <thinking>"
-inputs = tokenizer(prompt_for_step1, return_tensors="pt", padding=True).to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=50)
 # The expected output should be 'Modify Chart', as this is a refinement of the previous chart.

+---
+license: apache-2.0
+datasets:
+- GZUzxc/TaskDialogData
+language:
+- en
+metrics:
+- bleu
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+---
 ---
 # Model Card for TaskDialogViz
 # Example input: Simulating the second turn of a dialogue.
 # The first turn has already generated a bar chart comparing the average sales of different stores.
+input_text =
+    """<head> <field> Borough_Location, Park_Location, Sports_Played, Week_Start_Date,
+Week_End_Date, Sunday_Attendance, Monday_Attendance, Tuesday_Attendance,
+Wednesday_Attendance, Thursday_Attendance, Friday_Attendance, Saturday_Attendance,
+Attendance_Sum </field>
+<type> nominal, nominal,nominal,temporal, temporal, quantitative, quantitative, quantitative,
+quantitative, quantitative, quantitative, quantitative,quantitative </type>
+<data> <line 1> Bronx, Midland Beach, Basketball, Soccer, Flag Football, Kickball, 07/01/2018,
+07/31/2017, 850, 20, 9, 42, 15, 150, 93, 755 </line 1>
+<line 2> Manhattan, Williamsbridge Oval, Basketball, Soccer, Dodgeball, ultimate frisbee, 06/25/2017,
+04/28/2018, 250, 210, 650, 26, 480, 246, 155, 141 </line 2> </data>
+<previous utterance> Break it down by park location with different colors</previous utterance>
+<previous chart> {'analyzing task': 'Modify Chart', 'field': {'encoding': ['Park_Location',
+'Friday_Attendance', 'Borough_Location'], 'filter': ['Borough_Location']}, 'operations': ['encoding'],
+'mark': 'bar', 'encoding': {'x': {'field': 'Borough_Location'}, 'y': {'field': 'Friday_Attendance',
+'aggregate': 'sum'}, 'color': {'field': 'Park_Location'}}, 'filter': {'eq': ['Borough_Location', 'Manhattan']},
+'sort': {}} </previous chart>
+<utterance> how does Sunday attendance relate to Friday attendance in Manhattan parks? </utterance>"""
+inputs = tokenizer(input_text, return_tensors="pt", padding=True).to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=50)
 # The expected output should be 'Modify Chart', as this is a refinement of the previous chart.