Duplicate from openbmb/UltraInteract_pair

Co-authored-by: wanghanbin <hanbin@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,56 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+ultrainteract_preference_learning.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,111 @@
+---
+language:
+  - en
+license: mit
+pretty_name: UltraInteract_pair
+configs:
+  - config_name: default
+    data_files:
+      - split: train
+        path: ultrainteract_preference_learning.json
+dataset_info:
+  features:
+    - name: task
+      dtype: string
+    - name: dataset
+      dtype: string
+    - name: trajectory
+      list:
+        - name: from
+          dtype: string
+        - name: value
+          dtype: string
+    - name: chosen
+      dtype: string
+    - name: rejected
+      dtype: string
+    - name: id
+      dtype: string
+    - name: parent_id
+      dtype: string
+  splits:
+    - name: train
+      num_bytes: 1144517
+      num_examples: 219522
+  download_size: 1144517
+  dataset_size: 1144517
+---
+
+
+## Introduction
+
+- 📜 [Paper](https://github.com/OpenBMB/Eurus/tree/main)
+- 🤗 [Eurus Collection](https://huggingface.co/collections/openbmb/eurus-660bc40bec5376b3adc9d1c5)
+
+
+UltraInteract is a large-scale, high-quality alignment dataset specifically designed for complex reasoning tasks. For each instruction, it includes a preference tree consisting of
+- (1) reasoning chains with diverse planning strategies in a unified format
+- (2) multi-turn interaction trajectories with the environment and the critique
+- (3) pairwise data to facilitate preference learning
+
+## Structure
+UltraInteract collects a preference tree for each instruction, with the instruction being the root and each action a node. A trajectory is a root-to-leaf path consisting of a sequence of actions. In each preference tree, all nodes of correct actions and all trajectories ending with correct actions can be used for SFT. Paired correct and incorrect nodes or trajectories can be used for preference learning.
+<img src="./figures/tree.png" alt="tree" style="zoom: 20%;" />
+
+## Illustrative Example
+Here is an illustrative example of an UltraInteract trajectory over two turns. In each turn, the actor model generates step-by-step reasoning chains, and the environment and the critique model provide observations and textual critique respectively.
+<img src="./figures/ui_example.png" alt="ui_example" style="zoom: 25%;" />
+
+## Stats
+Below are some statistics about UltraInteract. It consists of 86k instructions, 286k correct answers, and 219k pairs.
+<img src="./figures/stats.png" alt="stats" style="zoom: 40%;" />
+
+
+## Dataset Format (Preference Learning)
+
+
+```JSONC
+{
+	"id": "d1f094e0e13096bc1bb6260e1e0d807e2c4ebfbbf4a4373f04cbed001c385c3c_5_3", // unique data id, contains three parts, the unique string, the depth of the preference tree, and current turn, separated by '_'
+	"parent_id": "d1f094e0e13096bc1bb6260e1e0d807e2c4ebfbbf4a4373f04cbed001c385c3c",  // data with the same parent_id have the same instruction but different actions.
+	"task": "Math_PoT", // task type, choices = ["Coding", "Math_Cot", "Math_PoT", "Logic"]
+	"dataset": "MATH", // the dataset where the instruction comes from
+    "trajectory": [
+        {
+            "from": "user",
+            "value": "Tool available:\n[1] Python interpreter\nWhen you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.\nSolve the following math problem step-by-step.\nSimplify your answer as much as possible.\nSimplify $(-3-2i)-(1+4i)$." // the task instruction
+        },
+        {
+            "from": "assistant",
+            "value": "Step 1: To simplify the expression $(-3-2i)-(1+4i)$, we need to distribute the negative sign to both terms inside the parentheses.\nStep 2: We can then combine like terms by adding the real parts and the imaginary parts separately.\n```python\n# Step 3: Distribute the negative sign to both terms inside the parentheses.\n(-3) - (-1) + (-2i) - (-4i)\n# Step 4: Combine like terms by adding the real parts and the imaginary parts separately.\n-3 + 1 + (-2i + 4i)\n```" // the assistant's action (turn 1)
+        },
+        {
+            "from": "user",
+            "value": "Out: Cell In[1], line 2\n    (-3) - (-1) + (-2i) - (-4i)\n                     ^\nSyntaxError: invalid syntax\nYour answer is wrong.\nYour thought process for simplifying the given complex numbers is correct. However, you made a syntax error in the code. In Python, the multiplication operation must be explicitly written out with an asterisk (*), even for complex numbers. Remember, the imaginary unit in Python is denoted as j and not i. Try correcting the syntax and calculate again."  // the observation from python interpreter and feedback (turn 1)
+        },
+        {
+            "from": "assistant",
+            "value": "Step 1: To simplify the expression $(-3-2i)-(1+4i)$, we need to distribute the negative sign to both terms inside the parentheses.\nStep 2: We can then combine like terms by adding the real parts and the imaginary parts separately.\n```python\n# Step 3: Distribute the negative sign to both terms inside the parentheses.\n(-3) - (-1) + (-2j) - (-4j)\n# Step 4: Combine like terms by adding the real parts and the imaginary parts separately.\n-3 + 1 + (-2j + 4j)\n```"  // the assistant's action acording to the observation and feedback.(turn 2)
+        },
+        {
+            "from": "user",
+            "value": "Out: (-2+2j)\nYour answer is wrong.\nYour thought process for simplifying the given complex numbers is on the right track. However, you made an arithmetic error when adding the real parts (-3 + 1 ≠ -2) and the imaginary parts (-2j + 4j ≠ 2j). You should have combined the like terms correctly to get the right answer -4 and -6j respectively. Please try again with the correct arithmetic calculations."  // the observation from python interpreter and feedback. (turn 2)
+        }
+    ] // trajectory is the interaction between user and assistant, and the first element is the task instruction.
+    "chosen": "Step 1: Split the expression into real and imaginary terms.\nStep 2: Subtract the real terms from each other.\nStep 3: Subtract the imaginary terms from each other.\nStep 4: Combine the results of the subtraction to get the simplified form of the expression.\n\n\n\n```python\n# Step 5:  Split the expression into real and imaginary parts and then subtract them.\nreal_part = -3 - 1  # Subtract the real parts\nimaginary_part = -2 - 4  # Subtract the imaginary parts\n# Step 6:  Combine the real and imaginary parts to get the result.\nresult = f\"{real_part}{imaginary_part:+d}i\"\nprint(result)\n```", // the chosen answer based on the trajectory.
+	"rejected": "Step 1: To simplify the expression $(-3-2i)-(1+4i)$, we need to distribute the negative sign to both terms inside the parentheses.\nStep 2: We can then combine like terms by adding the real parts and the imaginary parts separately.\n```python\n# Step 3: Distribute the negative sign to both terms inside the parentheses.\n(-3) - 1 - (-2j) - 4j\n# Step 4: Combine like terms by adding the real parts and the imaginary parts separately.\n-3 - 1 - 2j - 4j\n```",  // the rejected answer based on the trajectory.
+}
+```
+
+
+
+## Citation
+
+```bib
+@misc{yuan2024advancing,
+      title={Advancing LLM Reasoning Generalists with Preference Trees}, 
+      author={Lifan Yuan and Ganqu Cui and Hanbin Wang and Ning Ding and Xingyao Wang and Jia Deng and Boji Shan and Huimin Chen and Ruobing Xie and Yankai Lin and Zhenghao Liu and Bowen Zhou and Hao Peng and Zhiyuan Liu and Maosong Sun},
+      year={2024},
+      primaryClass={cs.CL}
+}
+```

ultrainteract_preference_learning.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f5c3363db2e3ec07eb6ee6a4db0204decbc06cf991f862b95abd42fdb1f140
+size 1171985818