Text Generation
Transformers
Safetensors
English
qwen3
math
reasoning
olympiad-math
supervised-fine-tuning
lora
cs-552
conversational
text-generation-inference
Instructions to use cs-552-2026-group1/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-group1/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-group1/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-group1/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-group1/math_model") 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-group1/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-group1/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-group1/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-group1/math_model
- SGLang
How to use cs-552-2026-group1/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-group1/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-group1/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-group1/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-group1/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-group1/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-group1/math_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +170 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-group1/math_model`](https://huggingface.co/cs-552-2026-group1/math_model)
|
| 4 |
+
- **Owner(s):** group **group1**
|
| 5 |
+
- **Generated at:** 2026-06-11T06:23:10+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:** [`04a59ca`](https://huggingface.co/cs-552-2026-group1/math_model/commit/04a59caae3c7206c40e83107be3ae79322ed41cd)
|
| 13 |
+
- **Message:** Submit model to HF
|
| 14 |
+
- **Committed:** 2026-06-10T21:15:26+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | 0.3200 | ok |
|
| 21 |
+
| Knowledge | — | not run |
|
| 22 |
+
| Multilingual | — | not run |
|
| 23 |
+
| Safety | — | not run |
|
| 24 |
+
|
| 25 |
+
## Sample completions
|
| 26 |
+
|
| 27 |
+
_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
|
| 28 |
+
|
| 29 |
+
### Math
|
| 30 |
+
|
| 31 |
+
**Correct** (1 shown)
|
| 32 |
+
|
| 33 |
+
- **reference**: `\frac{639}{40}`
|
| 34 |
+
- **overall** (8/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `\frac{639}{40}`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
1. **Identify the given information:**
|
| 41 |
+
- On the map, a length of $3$ inches represents $10$ miles in the real world.
|
| 42 |
+
- The actual distance between two buildings is $53.25$ miles.
|
| 43 |
+
|
| 44 |
+
2. **Set up the proportion:**
|
| 45 |
+
- Let $x$ be the distance between the buildings on the map in inches.
|
| 46 |
+
- The proportion can be set up as:
|
| 47 |
+
\[
|
| 48 |
+
\frac{3 \text{ inches}}{10 \text{ miles}} = \frac{x \text{ inches}}{53.25 \text{ miles}}
|
| 49 |
+
\]
|
| 50 |
+
|
| 51 |
+
3. **Cross-multiply to solve for $x$:**
|
| 52 |
+
\[
|
| 53 |
+
3 \times 53.25 = 10 \times x
|
| 54 |
+
\]
|
| 55 |
+
\[
|
| 56 |
+
159.75 = 10x
|
| 57 |
+
\]
|
| 58 |
+
|
| 59 |
+
4. **Solve for $x$:**
|
| 60 |
+
\[
|
| 61 |
+
x = \frac{159.75}{10}
|
| 62 |
+
\]
|
| 63 |
+
\[
|
| 64 |
+
x = 15.975
|
| 65 |
+
\]
|
| 66 |
+
|
| 67 |
+
5. **Convert the decimal to a fraction:**
|
| 68 |
+
- The decimal $15.975$ can be written as:
|
| 69 |
+
\[
|
| 70 |
+
15.975 = 15 + 0.975
|
| 71 |
+
\]
|
| 72 |
+
- Convert $0.975$ to a fraction:
|
| 73 |
+
\[
|
| 74 |
+
0.975 = \frac{975}{1000}
|
| 75 |
+
\]
|
| 76 |
+
- Simplify $\frac{975}{1000}$ by dividing both the numerator and the denominator by their greatest common divisor, which is $25$:
|
| 77 |
+
\[
|
| 78 |
+
\frac{975}{1000} = \frac{39}{40}
|
| 79 |
+
\]
|
| 80 |
+
- Therefore:
|
| 81 |
+
\[
|
| 82 |
+
15.975 = 15 + \frac{39}{40} = \frac{15 \times 40}{40} + \frac{39}{40} = \frac{600 + 39}{40} = \frac{639}{40}
|
| 83 |
+
\]
|
| 84 |
+
|
| 85 |
+
6. **Conclusion:**
|
| 86 |
+
- The distance between the buildings on the map, written as a fraction, is $\frac{639}{40}$ inches.
|
| 87 |
+
|
| 88 |
+
The final answer is $\boxed{\frac{639}{40}}$.
|
| 89 |
+
</think>
|
| 90 |
+
|
| 91 |
+
\boxed{\frac{639}{40}}
|
| 92 |
+
```
|
| 93 |
+
|
| 94 |
+
**Incorrect** (1 shown)
|
| 95 |
+
|
| 96 |
+
- **reference**: `2 - \frac{\pi}{2}`
|
| 97 |
+
- **overall** (0/8 completions correct)
|
| 98 |
+
- **extracted** (✗): `\frac{2}{3}`
|
| 99 |
+
- **completion**:
|
| 100 |
+
|
| 101 |
+
```text
|
| 102 |
+
<think>
|
| 103 |
+
1. **Define the problem and initial conditions:**
|
| 104 |
+
- Derek starts with a debt of $\pi$ MIT.
|
| 105 |
+
- Each day, he tosses a fair coin:
|
| 106 |
+
- Heads: Reduces debt by 1 MIT.
|
| 107 |
+
- Tails: Reduces debt by 2 MITs.
|
| 108 |
+
- If at any point his debt is nonpositive, he is considered debt-free.
|
| 109 |
+
- If his debt is positive, it is doubled after the payment.
|
| 110 |
+
|
| 111 |
+
2. **Define the probability of debt-free status
|
| 112 |
+
|
| 113 |
+
... [truncated 822 chars] ...
|
| 114 |
+
|
| 115 |
+
\frac{3}{2}}{2} = -\frac{1}{2}
|
| 116 |
+
\]
|
| 117 |
+
- The general solution to the recurrence relation is:
|
| 118 |
+
\[
|
| 119 |
+
p_n = A \cdot 1^n + B \cdot \left(-\frac{1}{2}\right)^n = A + B \left(-\frac{1}{2}\right)^n
|
| 120 |
+
\]
|
| 121 |
+
|
| 122 |
+
6. **Determine the constants $A$ and $B$:**
|
| 123 |
+
- Using the initial conditions $p_0 = 1$ and $p_1 = \frac{1}{2}$:
|
| 124 |
+
\[
|
| 125 |
+
p_0 = A + B = 1
|
| 126 |
+
\]
|
| 127 |
+
\[
|
| 128 |
+
p_1 = A + B \left(-\frac{1}{2}\right) = \frac{1}{2}
|
| 129 |
+
\]
|
| 130 |
+
- Solving these equations:
|
| 131 |
+
\[
|
| 132 |
+
A + B = 1
|
| 133 |
+
\]
|
| 134 |
+
\[
|
| 135 |
+
A - \frac{B}{2} = \frac{1}{2}
|
| 136 |
+
\]
|
| 137 |
+
\[
|
| 138 |
+
2A - B = 1
|
| 139 |
+
\]
|
| 140 |
+
\[
|
| 141 |
+
2A - B = 1
|
| 142 |
+
\]
|
| 143 |
+
\[
|
| 144 |
+
2A - (1 - A) = 1
|
| 145 |
+
\]
|
| 146 |
+
\[
|
| 147 |
+
3A = 2
|
| 148 |
+
\]
|
| 149 |
+
\[
|
| 150 |
+
A = \frac{2}{3}
|
| 151 |
+
\]
|
| 152 |
+
\[
|
| 153 |
+
B = 1 - A = 1 - \frac{2}{3} = \frac{1}{3}
|
| 154 |
+
\]
|
| 155 |
+
|
| 156 |
+
7. **Find the probability for $n = \pi$:**
|
| 157 |
+
- Substitute $n = \pi$ into the general solution:
|
| 158 |
+
\[
|
| 159 |
+
p_\pi = \frac{2}{3} + \frac{1}{3} \left(-\frac{1}{2}\right)^\pi
|
| 160 |
+
\]
|
| 161 |
+
- Since $\left(-\frac{1}{2}\right)^\pi$ is a very small number (approaching 0 as $\pi$ increases), we can approximate:
|
| 162 |
+
\[
|
| 163 |
+
p_\pi \approx \frac{2}{3}
|
| 164 |
+
\]
|
| 165 |
+
|
| 166 |
+
The final answer is $\boxed{\frac{2}{3}}$.
|
| 167 |
+
</think>
|
| 168 |
+
|
| 169 |
+
\boxed{\frac{2}{3}}
|
| 170 |
+
```
|