Update README.md

README.md

@@ -17,13 +17,150 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
 
+Example 1)
+
+```python
+from datasets import load_dataset
+from transformers import pipeline
+import os
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+
+model_name = "plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.2"
+
+pipe = pipeline("token-classification", model=model_name, device="cuda")
+dataset = load_dataset("trl-lib/math_shepherd")
+example = dataset["test"][10]
+
+sep = "\n"
+
+print(sep.join((example["prompt"], *example["completions"])))
+for idx in range(1, len(example["completions"])+1):
+    text = sep.join((example["prompt"], *example["completions"][0:idx])) + sep
+    output = pipe(text)
+    score = float(output[-1]["score"])
+    pred = True if output[-1]["entity"] == "LABEL_1" else False
+    print(f"Step {idx}\tPredicted (score): {pred} ({score:.2f})\tLabel: {example['labels'][idx-1]}")
+
+# Grandma gave Bryce and Carter some raisins. Bryce received 6 more raisins than Carter, and Carter received half the number of raisins Bryce received. How many raisins did Bryce receive?
+# Step 1: Let $b$ be the number of raisins Bryce received and $c$ be the number of raisins Carter received.
+# Step 2: We are given that $b = c + 6$ and $c = \frac{1}{2}b$.
+# Step 3: Substituting the second equation into the first equation, we get $b = c + 6 = \frac{1}{2}b + 6$.
+# Step 4: Simplifying, we have $b = \frac{1}{2}b + 6$.
+# Step 5: Subtracting $\frac{1}{2}b$ from both sides, we get $\frac{1}{2}b - b = 6$.
+# Step 6: Simplifying further, we have $\frac{1}{2}b - 2b = 6$.
+# Step 7: Combining like terms, we have $-\frac{1}{2}b = 6$.
+# Step 8: Multiplying both sides by $-2$, we get $b = -12$.
+# Step 9: Therefore, Bryce received $\boxed{-12}$ raisins.The answer is: -12
+# Step 1  Predicted (score): True (0.99)  Label: True
+# Step 2  Predicted (score): True (0.94)  Label: True
+# Step 3  Predicted (score): True (0.94)  Label: True
+# Step 4  Predicted (score): True (0.82)  Label: True
+# Step 5  Predicted (score): True (0.50)  Label: True
+# Step 6  Predicted (score): False (0.71) Label: False
+# Step 7  Predicted (score): False (0.73) Label: False
+# Step 8  Predicted (score): False (0.77) Label: False
+# Step 9  Predicted (score): False (0.97) Label: False
+```
+
+
+Example 2)
+
 ```python
+from datasets import load_dataset
 from transformers import pipeline
+import os
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+
+model_name = "plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.2"
+
+pipe = pipeline("token-classification", model=model_name, device="cuda")
+dataset = load_dataset("trl-lib/math_shepherd")
+i = 32 # 10, 32
+example = dataset["test"][i]
+
+sep = "\n"
+
+print(sep.join((example["prompt"], *example["completions"])))
+for idx in range(1, len(example["completions"])+1):
+    text = sep.join((example["prompt"], *example["completions"][0:idx])) + sep
+    output = pipe(text)
+    score = float(output[-1]["score"])
+    pred = True if output[-1]["entity"] == "LABEL_1" else False
+    print(f"Step {idx}\tPredicted (score): {pred} ({score:.2f})\tLabel: {example['labels'][idx-1]}")
+
+
+# In the Golden State Team, each player earned points. Draymond earned 12 points, Curry earned twice the points as Draymond, Kelly earned 9, Durant earned twice the points as Kelly, Klay earned half the points as Draymond. How many points did the Golden States have in total?
+# Step 1: Draymond earned 12 points, Curry earned twice the points as Draymond, which is 2*12 = 24 points.
+# Step 2: Kelly earned 9 points, Durant earned twice the points as Kelly, which is 2*9 = 18 points.
+# Step 3: Klay earned half the points as Draymond, which is 12/2 = <<12/2=6>>6 points.
+# Step 4: The Golden State Team had 12+24+9+18+6 = <<12+24+9+18+6=51>>51 points. The answer is: 51
+# Step 1  Predicted (score): True (1.00)  Label: True
+# Step 2  Predicted (score): True (1.00)  Label: True
+# Step 3  Predicted (score): True (1.00)  Label: True
+# Step 4  Predicted (score): False (0.99) Label: False
+```
+
+Example 3)
+
+This example corresponds to the one shown in the [peiyi9979/math-shepherd-mistral-7b-prm](https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm):
+
+```python
+from datasets import load_dataset
+from transformers import pipeline
+import os
+os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+
+model_name = "plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.2"
+
+pipe = pipeline("token-classification", model=model_name, device="cuda")
+
+examples = [
+    {
+        "prompt": "Janet\u2019s ducks lay 16 eggs per day. She eats three for breakfast every morning and bakes muffins for her friends every day with four. She sells the remainder at the farmers' market daily for $2 per fresh duck egg. How much in dollars does she make every day at the farmers' market?",
+        "completions": [
+            "Step 1: Janet's ducks lay 16 eggs per day.",
+            'Step 2: She eats three for breakfast every morning, so she has 16 - 3 = 13 eggs left.',
+            'Step 3: She bakes muffins for her friends every day with four eggs, so she has 13 - 4 = 9 eggs left.',
+            "Step 4: She sells the remainder at the farmers' market daily for $2 per fresh duck egg, so she makes 9 * $2 = $18 every day at the farmers' market. The answer is: 18"
+        ],
+        "labels": [True, True, True, True]
+    },
+    {
+        "prompt": "Janet\u2019s ducks lay 16 eggs per day. She eats three for breakfast every morning and bakes muffins for her friends every day with four. She sells the remainder at the farmers' market daily for $2 per fresh duck egg. How much in dollars does she make every day at the farmers' market?",
+        "completions": [
+            "Step 1: Janet's ducks lay 16 eggs per day.",
+            'Step 2: She eats three for breakfast every morning, so she has 16 - 3 = 13 eggs left.',
+            'Step 3: She bakes muffins for her friends every day with four eggs, so she has 13 - 4 = 9 eggs left.',
+            "Step 4: She sells the remainder at the farmers' market daily for $2 per fresh duck egg, so she makes 9 * $2 = $18 every day at the farmers' market. The answer is: 17"
+        ],
+        "labels": [True, True, True, False]
+    },
+    
+]
+
+
+sep = "\n"
+
+for i, example in enumerate(examples):
+    print(f"- Example {i}:")
+    for idx in range(1, len(example["completions"])+1):
+        text = "\n".join((example["prompt"], *example["completions"][0:idx])) + "\n"
+        output = pipe(text)
+        score = float(output[-1]["score"])
+        pred = True if output[-1]["entity"] == "LABEL_1" else False
+        print(f"Step {idx}\tPredicted (score): {pred} ({score:.2f})\tLabel: {example['labels'][idx-1]}")
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.2", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+# - Example 0:
+# Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.
+# Step 1  Predicted (score): True (0.98)  Label: True
+# Step 2  Predicted (score): True (0.87)  Label: True
+# Step 3  Predicted (score): True (0.93)  Label: True
+# Step 4  Predicted (score): True (0.98)  Label: True
+# - Example 1:
+# Step 1  Predicted (score): True (0.98)  Label: True
+# Step 2  Predicted (score): True (0.87)  Label: True
+# Step 3  Predicted (score): True (0.93)  Label: True
+# Step 4  Predicted (score): False (0.99) Label: False
 ```
 
 ## Training procedure