Text Generation
PEFT
Safetensors
Transformers
qwen3
grpo
lora
trl
conversational
text-generation-inference
Instructions to use cs-552-2026-thinking-tokens/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cs-552-2026-thinking-tokens/math_model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B") model = PeftModel.from_pretrained(base_model, "cs-552-2026-thinking-tokens/math_model") - Transformers
How to use cs-552-2026-thinking-tokens/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-thinking-tokens/math_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-thinking-tokens/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-thinking-tokens/math_model", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cs-552-2026-thinking-tokens/math_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cs-552-2026-thinking-tokens/math_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-thinking-tokens/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-thinking-tokens/math_model
- SGLang
How to use cs-552-2026-thinking-tokens/math_model with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "cs-552-2026-thinking-tokens/math_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-thinking-tokens/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "cs-552-2026-thinking-tokens/math_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-thinking-tokens/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-thinking-tokens/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-thinking-tokens/math_model
Update Automated MNLP evaluation report (2026-06-08)
Browse files- EVAL_REPORT.md +24 -161
EVAL_REPORT.md
CHANGED
|
@@ -2,22 +2,22 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-thinking-tokens/math_model`](https://huggingface.co/cs-552-2026-thinking-tokens/math_model)
|
| 4 |
- **Owner(s):** group **thinking-tokens**
|
| 5 |
-
- **Generated at:** 2026-06-
|
| 6 |
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
|
| 8 |
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
| 9 |
|
| 10 |
## Evaluated checkpoint
|
| 11 |
|
| 12 |
-
- **Commit:** [`
|
| 13 |
- **Message:** Upload folder using huggingface_hub
|
| 14 |
-
- **Committed:** 2026-
|
| 15 |
|
| 16 |
## Summary
|
| 17 |
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
-
| Math | 0.
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
@@ -30,179 +30,42 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
-
- **reference**: `
|
| 34 |
- **overall** (8/8 completions correct)
|
| 35 |
-
- **extracted** (✓): `
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
- Actual distance between two buildings: $ 53.25 $ miles.
|
| 43 |
-
- We are to find the map distance in inches.
|
| 44 |
-
|
| 45 |
-
---
|
| 46 |
-
|
| 47 |
-
### Step 1: Determine the scale factor
|
| 48 |
-
|
| 49 |
-
We know that:
|
| 50 |
-
|
| 51 |
-
$$
|
| 52 |
-
3 \text{ inches} = 10 \text{ miles}
|
| 53 |
-
$$
|
| 54 |
-
|
| 55 |
-
We want to find how many inches represent $ 1 $ mile.
|
| 56 |
-
|
| 57 |
-
$$
|
| 58 |
-
\text{Scale factor} = \frac{3}{10} \text{ inches per mile}
|
| 59 |
-
$$
|
| 60 |
-
|
| 61 |
-
---
|
| 62 |
-
|
| 63 |
-
### Step 2: Use the scale factor to find the map distance
|
| 64 |
-
|
| 65 |
-
We are given:
|
| 66 |
-
|
| 67 |
-
$$
|
| 68 |
-
53.25 \text{ miles} \times \frac{3}{10} \text{ inches/mile} = ?
|
| 69 |
-
$$
|
| 70 |
-
|
| 71 |
-
$$
|
| 72 |
-
\text{Map distance} = 53.25 \times \frac{3}{10}
|
| 73 |
-
$$
|
| 74 |
-
|
| 75 |
$$
|
| 76 |
-
|
| 77 |
$$
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
$$
|
| 82 |
-
|
| 83 |
$$
|
| 84 |
-
|
| 85 |
$$
|
|
|
|
|
|
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
### Step 3: Convert to a fraction
|
| 90 |
-
|
| 91 |
-
We now convert $ 15.975 $ into a fraction.
|
| 92 |
-
|
| 93 |
-
$$
|
| 94 |
-
15.975 = 15 + 0.975
|
| 95 |
-
$$
|
| 96 |
-
|
| 97 |
-
$$
|
| 98 |
-
0.975 = \frac{975}{1000}
|
| 99 |
-
$$
|
| 100 |
-
|
| 101 |
-
$$
|
| 102 |
-
\frac{975}{1000} = \frac{39}{40} \quad \text{(simplify by dividing numerator and denominator by 25)}
|
| 103 |
-
$$
|
| 104 |
-
|
| 105 |
-
So:
|
| 106 |
-
|
| 107 |
-
$$
|
| 108 |
-
15.975 = 15 + \frac{39}{40} = \frac{600}{40} + \frac{39}{40} = \frac{639}{40}
|
| 109 |
-
$$
|
| 110 |
-
|
| 111 |
-
---
|
| 112 |
-
|
| 113 |
-
### Final Answer:
|
| 114 |
-
|
| 115 |
-
$$
|
| 116 |
-
\boxed{\frac{639}{40}} \text{ inches}
|
| 117 |
-
$$
|
| 118 |
```
|
| 119 |
|
| 120 |
**Incorrect** (1 shown)
|
| 121 |
|
| 122 |
-
- **reference**: `
|
| 123 |
- **overall** (0/8 completions correct)
|
| 124 |
-
- **extracted** (✗): `
|
| 125 |
- **completion**:
|
| 126 |
|
| 127 |
```text
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
- Interpret the digit string of $ n $ as a number in base $ b $, and compute its value as $ f(n) $.
|
| 133 |
-
|
| 134 |
-
We are to find how many such $ n < 1000 $ satisfy $ f(n) = n $.
|
| 135 |
-
|
| 136 |
-
---
|
| 137 |
-
|
| 138 |
-
### Ste
|
| 139 |
-
|
| 140 |
-
... [truncated 823 chars] ...
|
| 141 |
-
|
| 142 |
-
1 \cdot 2^0 = 4 + 2 + 1 = 7 \neq 111 $: ❌
|
| 143 |
-
|
| 144 |
-
Try $ n = 199 $:
|
| 145 |
-
|
| 146 |
-
- $ b = 10 $
|
| 147 |
-
- $ f(199) = 1 \cdot 10^2 + 9 \cdot 10^1 + 9 \cdot 10^0 = 100 + 90 + 9 = 199 $: ✅
|
| 148 |
-
|
| 149 |
-
So $ n = 199 $ works.
|
| 150 |
-
|
| 151 |
-
Try $ n = 299 $:
|
| 152 |
-
|
| 153 |
-
- $ f(299) = 2 \cdot 100 + 9 \cdot 10 + 9 = 299 $: ✅
|
| 154 |
-
|
| 155 |
-
Try $ n = 399 $:
|
| 156 |
-
|
| 157 |
-
- $ f(399) = 3 \cdot 100 + 9 \cdot 10 + 9 = 399 $: ✅
|
| 158 |
-
|
| 159 |
-
Try $ n = 499 $:
|
| 160 |
-
|
| 161 |
-
- $ f(499) = 4 \cdot 100 + 9 \cdot 10 + 9 = 499 $: ✅
|
| 162 |
-
|
| 163 |
-
Try $ n = 599 $:
|
| 164 |
-
|
| 165 |
-
- $ f(599) = 5 \cdot 100 + 9 \cdot 10 + 9 = 599 $: ✅
|
| 166 |
-
|
| 167 |
-
Try $ n = 699 $:
|
| 168 |
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
Try $ n = 799 $:
|
| 172 |
-
|
| 173 |
-
- $ f(799) = 7 \cdot 100 + 9 \cdot 10 + 9 = 799 $: ✅
|
| 174 |
-
|
| 175 |
-
Try $ n = 899 $:
|
| 176 |
-
|
| 177 |
-
- $ f(899) = 8 \cdot 100 + 9 \cdot 10 + 9 = 899 $: ✅
|
| 178 |
-
|
| 179 |
-
Try $ n = 999 $:
|
| 180 |
-
|
| 181 |
-
- $ f(999) = 9 \cdot 100 + 9 \cdot 10 + 9 = 999 $: ✅
|
| 182 |
-
|
| 183 |
-
So all three-digit numbers where the last two digits are 99 (i.e., 199, 299, ..., 999) satisfy $ f(n) = n $.
|
| 184 |
-
|
| 185 |
-
That's 9 numbers.
|
| 186 |
-
|
| 187 |
-
---
|
| 188 |
-
|
| 189 |
-
### Step 7: Count all valid numbers
|
| 190 |
-
|
| 191 |
-
- **Single-digit numbers**: 1 to 9 → 9 numbers
|
| 192 |
-
- **Two-digit numbers**: 19, 29, ..., 99 → 9 numbers
|
| 193 |
-
- **Three-digit numbers**: 199, 299, ..., 999 → 9 numbers
|
| 194 |
-
|
| 195 |
-
So total number of such $ n < 1000 $ is:
|
| 196 |
-
|
| 197 |
-
$$
|
| 198 |
-
\boxed{9 + 9 + 9 = 27}
|
| 199 |
-
$$
|
| 200 |
-
|
| 201 |
-
---
|
| 202 |
-
|
| 203 |
-
### ✅ Final Answer:
|
| 204 |
-
|
| 205 |
-
$$
|
| 206 |
-
\boxed{27}
|
| 207 |
-
$$
|
| 208 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-thinking-tokens/math_model`](https://huggingface.co/cs-552-2026-thinking-tokens/math_model)
|
| 4 |
- **Owner(s):** group **thinking-tokens**
|
| 5 |
+
- **Generated at:** 2026-06-08T04:40:54+00:00 (UTC)
|
| 6 |
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
|
| 8 |
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
| 9 |
|
| 10 |
## Evaluated checkpoint
|
| 11 |
|
| 12 |
+
- **Commit:** [`b808807`](https://huggingface.co/cs-552-2026-thinking-tokens/math_model/commit/b80880717f0a37b231da02f24ae9fa34b70747b9)
|
| 13 |
- **Message:** Upload folder using huggingface_hub
|
| 14 |
+
- **Committed:** 2026-06-06T17:57:58+00:00
|
| 15 |
|
| 16 |
## Summary
|
| 17 |
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
+
| Math | 0.2900 | ok |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `4`
|
| 34 |
- **overall** (8/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `4`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
+
<think>
|
| 40 |
+
Solution 1
|
| 41 |
+
We rewrite the equation as
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
$$
|
| 43 |
+
10^x=10+9990=10000
|
| 44 |
$$
|
| 45 |
+
Since $10^4=10000$, we have $x=4$.
|
| 46 |
+
Solution 2
|
| 47 |
+
We rewrite the equation as
|
|
|
|
|
|
|
| 48 |
$$
|
| 49 |
+
10^x=10+9990=10+999 \cdot 10=10(1+999)=10000
|
| 50 |
$$
|
| 51 |
+
Since $10^4=10000$, we have $x=4$.
|
| 52 |
+
</think>
|
| 53 |
|
| 54 |
+
Therefore, the final answer is \boxed{4}.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
```
|
| 56 |
|
| 57 |
**Incorrect** (1 shown)
|
| 58 |
|
| 59 |
+
- **reference**: `1305`
|
| 60 |
- **overall** (0/8 completions correct)
|
| 61 |
+
- **extracted** (✗): `18`
|
| 62 |
- **completion**:
|
| 63 |
|
| 64 |
```text
|
| 65 |
+
<think>
|
| 66 |
+
The number of divisors of a positive integer $n$ is smallest when it is a product of the first few primes. We will try small prime factors first.
|
| 67 |
+
The smallest imbalanced multiple of $2000$ is $2000 \times 2 = 4000$, which has divisors $1, 2, 4, 5, 8, 10, 16, 20, 25, 40, 50, 80, 100, 200, 250, 400, 500, 1000, 2000$. This number has 18 divisors.
|
| 68 |
+
</think>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
+
Therefore, the final answer is \boxed{18}.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
```
|