Instructions to use cs-552-2026-OAAA/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-OAAA/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-OAAA/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-OAAA/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-OAAA/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-OAAA/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-OAAA/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-OAAA/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-OAAA/math_model
- SGLang
How to use cs-552-2026-OAAA/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-OAAA/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-OAAA/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-OAAA/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-OAAA/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-OAAA/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-OAAA/math_model
Update Automated MNLP evaluation report (2026-06-05)
Browse files- EVAL_REPORT.md +68 -67
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-OAAA/math_model`](https://huggingface.co/cs-552-2026-OAAA/math_model)
|
| 4 |
- **Owner(s):** group **OAAA**
|
| 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._
|
|
@@ -11,7 +11,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
-
| Math | 0.
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
@@ -24,149 +24,150 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
-
- **overall** (
|
| 29 |
-
- **extracted** (✓): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
-
Okay, so I need to
|
| 35 |
|
| 36 |
-
|
| 37 |
-
\sum_{i=1}^{2023} \frac{a_i - a_{i-1}}{a_{i+1} - a_i}
|
| 38 |
-
$$
|
| 39 |
-
|
| 40 |
-
given that $a_1, \ldots, a_{2024}$ are positive real numbers with $a_{i+1} \ge 2a_i$ for each $i = 1, \ldots, 2023$, and $a_0 = 0$.
|
| 41 |
-
|
| 42 |
-
First, let me try to understand the problem. We have a sequence starting at 0, and each term is at least twice the previous one. The
|
| 43 |
|
| 44 |
... [truncated 823 chars] ...
|
| 45 |
|
| 46 |
-
|
| 47 |
-
$$
|
| 48 |
|
| 49 |
-
|
| 50 |
|
| 51 |
$$
|
| 52 |
-
\
|
| 53 |
$$
|
| 54 |
|
| 55 |
-
|
| 56 |
|
| 57 |
$$
|
| 58 |
-
\
|
| 59 |
$$
|
| 60 |
|
| 61 |
-
|
| 62 |
|
| 63 |
$$
|
| 64 |
-
\
|
| 65 |
$$
|
| 66 |
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
Since $ a_i = 2a_{i-1} $, we have:
|
| 70 |
|
| 71 |
$$
|
| 72 |
-
\
|
| 73 |
$$
|
| 74 |
|
| 75 |
-
|
| 76 |
|
| 77 |
-
$$
|
| 78 |
-
|
| 79 |
-
$$
|
| 80 |
|
| 81 |
-
|
| 82 |
|
| 83 |
$$
|
| 84 |
-
|
| 85 |
$$
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
### Step 3: Generalize the Result
|
| 90 |
-
|
| 91 |
-
In general, for a sequence of length $ n $ (i.e., $ a_0, a_1, \ldots, a_n $), with the constraint $ a_{i+1} \ge 2a_i $, the maximum sum is:
|
| 92 |
|
| 93 |
$$
|
| 94 |
-
\
|
| 95 |
$$
|
| 96 |
|
| 97 |
-
|
| 98 |
|
| 99 |
-
|
| 100 |
-
\frac{2024}{2} = \boxed{1012}
|
| 101 |
-
$$
|
| 102 |
|
| 103 |
-
-
|
| 104 |
|
| 105 |
-
|
| 106 |
|
| 107 |
$$
|
| 108 |
-
\boxed{
|
| 109 |
$$
|
| 110 |
```
|
| 111 |
|
| 112 |
**Incorrect** (1 shown)
|
| 113 |
|
| 114 |
-
- **reference**: `$
|
| 115 |
- **overall** (0/8 completions correct)
|
| 116 |
-
- **extracted** (✗): `
|
| 117 |
- **completion**:
|
| 118 |
|
| 119 |
```text
|
| 120 |
<think>
|
| 121 |
-
Okay, so I need to
|
| 122 |
|
| 123 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
|
| 125 |
... [truncated 822 chars] ...
|
| 126 |
|
| 127 |
-
|
| 128 |
|
| 129 |
-
|
|
|
|
|
|
|
| 130 |
|
| 131 |
-
|
| 132 |
|
| 133 |
-
|
|
|
|
|
|
|
| 134 |
|
| 135 |
-
|
| 136 |
|
| 137 |
$$
|
| 138 |
-
|
| 139 |
$$
|
| 140 |
|
| 141 |
-
This
|
|
|
|
|
|
|
| 142 |
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
|
| 147 |
-
|
| 148 |
|
| 149 |
$$
|
| 150 |
-
a
|
| 151 |
$$
|
| 152 |
|
| 153 |
-
|
| 154 |
|
| 155 |
---
|
| 156 |
|
| 157 |
-
### Step 4:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
|
| 159 |
-
|
|
|
|
| 160 |
|
| 161 |
-
|
| 162 |
-
- Any deviation from this form leads to contradictions or non-integer values for $ F(a) $.
|
| 163 |
-
- There are no other functions $ F $ that satisfy the condition for all $ a, b \in \mathbb{Z}_{>0} $.
|
| 164 |
|
| 165 |
---
|
| 166 |
|
| 167 |
### Final Answer
|
| 168 |
|
| 169 |
$$
|
| 170 |
-
\boxed{
|
| 171 |
$$
|
| 172 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-OAAA/math_model`](https://huggingface.co/cs-552-2026-OAAA/math_model)
|
| 4 |
- **Owner(s):** group **OAAA**
|
| 5 |
+
- **Generated at:** 2026-06-05T03:00:32+00:00 (UTC)
|
| 6 |
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
|
| 8 |
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
|
|
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
+
| Math | 0.4200 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `510`
|
| 28 |
+
- **overall** (1/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `510`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
+
Okay, so I need to solve this problem about points on the plane x + y + z = 75 with coordinates satisfying x - yz < y - zx < z - xy. The set is divided into three disjoint convex regions, and exactly one of them has finite area. I need to find that area in the form a√b and then compute a + b.
|
| 35 |
|
| 36 |
+
First, let me try to understand the given inequality conditions. The problem states that for poin
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
... [truncated 823 chars] ...
|
| 39 |
|
| 40 |
+
o the area element on the plane is $\sqrt{3} \, dx \, dy$.
|
|
|
|
| 41 |
|
| 42 |
+
The area of the region is therefore:
|
| 43 |
|
| 44 |
$$
|
| 45 |
+
\text{Area} = \sqrt{3} \int_{x=-1}^{25} \int_{y=x}^{\frac{75 - x}{2}} dy \, dx
|
| 46 |
$$
|
| 47 |
|
| 48 |
+
Compute the inner integral:
|
| 49 |
|
| 50 |
$$
|
| 51 |
+
\int_{x}^{\frac{75 - x}{2}} dy = \frac{75 - x}{2} - x = \frac{75 - 3x}{2}
|
| 52 |
$$
|
| 53 |
|
| 54 |
+
Now compute the outer integral:
|
| 55 |
|
| 56 |
$$
|
| 57 |
+
\int_{-1}^{25} \frac{75 - 3x}{2} dx = \frac{1}{2} \int_{-1}^{25} (75 - 3x) dx
|
| 58 |
$$
|
| 59 |
|
| 60 |
+
Compute the antiderivative:
|
|
|
|
|
|
|
| 61 |
|
| 62 |
$$
|
| 63 |
+
\int (75 - 3x) dx = 75x - \frac{3}{2}x^2
|
| 64 |
$$
|
| 65 |
|
| 66 |
+
Evaluate from $x = -1$ to $x = 25$:
|
| 67 |
|
| 68 |
+
- At $x = 25$: $75(25) - \frac{3}{2}(25)^2 = 1875 - \frac{1875}{2} = \frac{1875}{2}$
|
| 69 |
+
- At $x = -1$: $75(-1) - \frac{3}{2}(1)^2 = -75 - \frac{3}{2} = -\frac{153}{2}$
|
|
|
|
| 70 |
|
| 71 |
+
So the integral is:
|
| 72 |
|
| 73 |
$$
|
| 74 |
+
\frac{1}{2} \left( \frac{1875}{2} - \left(-\frac{153}{2} \right) \right) = \frac{1}{2} \cdot \frac{2028}{2} = \frac{1014}{2} = 507
|
| 75 |
$$
|
| 76 |
|
| 77 |
+
Thus, the area of the region in the plane is:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
|
| 79 |
$$
|
| 80 |
+
\text{Area} = \sqrt{3} \cdot 507 = 507\sqrt{3}
|
| 81 |
$$
|
| 82 |
|
| 83 |
+
---
|
| 84 |
|
| 85 |
+
### Step 4: Final Answer
|
|
|
|
|
|
|
| 86 |
|
| 87 |
+
We are told the finite area is of the form $a\sqrt{b}$, with $a$ and $b$ integers and $b$ square-free.
|
| 88 |
|
| 89 |
+
From the above, $a = 507$ and $b = 3$. Since $3$ is square-free, we compute:
|
| 90 |
|
| 91 |
$$
|
| 92 |
+
a + b = 507 + 3 = \boxed{510}
|
| 93 |
$$
|
| 94 |
```
|
| 95 |
|
| 96 |
**Incorrect** (1 shown)
|
| 97 |
|
| 98 |
+
- **reference**: `$g(x)=c, g(x)=\lceil x \rceil, g(x)=\lfloor x \rfloor$`
|
| 99 |
- **overall** (0/8 completions correct)
|
| 100 |
+
- **extracted** (✗): `x`
|
| 101 |
- **completion**:
|
| 102 |
|
| 103 |
```text
|
| 104 |
<think>
|
| 105 |
+
Okay, so I need to figure out all mappings $ h: \mathbb{Q} \to \mathbb{Z} $ that satisfy the equation:
|
| 106 |
|
| 107 |
+
$$
|
| 108 |
+
h(x) = h\left( \frac{h(bx - a) + a}{b} \right)
|
| 109 |
+
$$
|
| 110 |
+
|
| 111 |
+
for every $ x \in \mathbb{Q} $, every integer $ a $, and every positive integer $ b $.
|
| 112 |
+
|
| 113 |
+
First, let me try to understand the problem. The function $ h $ takes a rational number $ x $ and maps it to an integer. The equation given relat
|
| 114 |
|
| 115 |
... [truncated 822 chars] ...
|
| 116 |
|
| 117 |
+
$ h(x) = kx $:
|
| 118 |
|
| 119 |
+
$$
|
| 120 |
+
kx = k^2 x + \frac{k a (1 - k)}{b}
|
| 121 |
+
$$
|
| 122 |
|
| 123 |
+
Subtract $ k^2 x $ from both sides:
|
| 124 |
|
| 125 |
+
$$
|
| 126 |
+
kx(1 - k) = \frac{k a (1 - k)}{b}
|
| 127 |
+
$$
|
| 128 |
|
| 129 |
+
Divide both sides by $ k $ (assuming $ k \ne 0 $):
|
| 130 |
|
| 131 |
$$
|
| 132 |
+
x(1 - k) = \frac{a(1 - k)}{b}
|
| 133 |
$$
|
| 134 |
|
| 135 |
+
This must hold for **all** $ x \in \mathbb{Q} $ and **all** $ a \in \mathbb{Z} $, which is only possible if $ 1 - k = 0 $, i.e., $ k = 1 $.
|
| 136 |
+
|
| 137 |
+
Thus, the only linear solution is:
|
| 138 |
|
| 139 |
+
$$
|
| 140 |
+
h(x) = x
|
| 141 |
+
$$
|
| 142 |
|
| 143 |
+
If $ k = 0 $, then $ h(x) = 0 $, and we check:
|
| 144 |
|
| 145 |
$$
|
| 146 |
+
h(x) = h\left( \frac{h(bx - a) + a}{b} \right) = h\left( \frac{0 + a}{b} \right) = h\left( \frac{a}{b} \right) = 0
|
| 147 |
$$
|
| 148 |
|
| 149 |
+
So $ h(x) = 0 $ also satisfies the equation.
|
| 150 |
|
| 151 |
---
|
| 152 |
|
| 153 |
+
### Step 4: Are There Other Solutions?
|
| 154 |
+
|
| 155 |
+
Suppose $ h(x) $ is not linear. Then, from the earlier relation $ h(bx) = b h(x) $, it follows that $ h $ is **linear** over $ \mathbb{Q} $, because:
|
| 156 |
+
|
| 157 |
+
- For any rational $ x = \frac{m}{n} $, $ h(x) = h\left( \frac{m}{n} \right) = \frac{m}{n} h(1) $, so $ h $ is linear.
|
| 158 |
+
|
| 159 |
+
Thus, the only possible solutions are:
|
| 160 |
|
| 161 |
+
- $ h(x) = 0 $, and
|
| 162 |
+
- $ h(x) = x $
|
| 163 |
|
| 164 |
+
These are the **only** functions from $ \mathbb{Q} \to \mathbb{Z} $ that satisfy the given equation.
|
|
|
|
|
|
|
| 165 |
|
| 166 |
---
|
| 167 |
|
| 168 |
### Final Answer
|
| 169 |
|
| 170 |
$$
|
| 171 |
+
\boxed{0} \quad \text{and} \quad \boxed{x}
|
| 172 |
$$
|
| 173 |
```
|