Instructions to use cs-552-2026-kth/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-kth/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-kth/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-kth/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-kth/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-kth/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-kth/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-kth/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-kth/math_model
- SGLang
How to use cs-552-2026-kth/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-kth/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-kth/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-kth/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-kth/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-kth/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-kth/math_model
Update Automated MNLP evaluation report (2026-06-08)
Browse files- EVAL_REPORT.md +42 -46
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-kth/math_model`](https://huggingface.co/cs-552-2026-kth/math_model)
|
| 4 |
- **Owner(s):** group **kth**
|
| 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._
|
|
@@ -17,7 +17,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 17 |
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
-
| Math | 0.
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
@@ -30,84 +30,80 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
-
- **reference**: `
|
| 34 |
-
- **overall** (
|
| 35 |
-
- **extracted** (✓): `
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
-
|
|
|
|
| 41 |
|
| 42 |
-
|
| 43 |
-
|
| 44 |
|
| 45 |
-
|
| 46 |
-
\[ f(-1) = \frac{3(-1) - 2}{-1 - 2} = \frac{-3 - 2}{-3} = \frac{-5}{-3} = \frac{5}{3} \]
|
| 47 |
|
| 48 |
-
|
| 49 |
-
\[ f(0) = \frac{3(0) - 2}{0 - 2} = \frac{0 - 2}{-2} = \frac{-2}{-2} = 1 \]
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
| 53 |
|
| 54 |
-
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
</think>
|
| 57 |
|
| 58 |
-
Therefore, the answer is \boxed{
|
| 59 |
```
|
| 60 |
|
| 61 |
**Incorrect** (1 shown)
|
| 62 |
|
| 63 |
-
- **reference**: `(
|
| 64 |
- **overall** (0/8 completions correct)
|
| 65 |
-
- **extracted** (✗): `
|
| 66 |
- **completion**:
|
| 67 |
|
| 68 |
```text
|
| 69 |
<think>
|
| 70 |
-
Let's
|
| 71 |
-
|
| 72 |
-
1. \(p\) is a prime greater than 2.
|
| 73 |
-
2. \(m\) and \(n\) are positive integers with \(m \le n\).
|
| 74 |
-
3. \(m^{p-1}+n\) and \(n^{p-1}+m\) are both powers of \(p\).
|
| 75 |
-
|
| 76 |
-
We can start by considering the possible values of \(p\). Since \(p\) is a prime greater than 2, the smallest possible value of \(p\) is 3.
|
| 77 |
-
|
| 78 |
-
Let's consider the case where \(p = 3\). We ne
|
| 79 |
|
| 80 |
-
|
|
|
|
| 81 |
|
| 82 |
-
|
| 83 |
|
| 84 |
-
|
| 85 |
-
\[
|
| 86 |
-
\[ n^{p-1}+m = b^{p} \]
|
| 87 |
|
| 88 |
-
|
| 89 |
|
| 90 |
-
|
| 91 |
-
\[
|
| 92 |
|
| 93 |
-
|
| 94 |
-
\[ (m-n)(m^{p-2}+m^{p-3}n+\cdots+n^{p-2}) = (a-b)(a^{p-1}+a^{p-2}b+\cdots+ab^{p-2}) \]
|
| 95 |
|
| 96 |
-
|
| 97 |
|
| 98 |
-
|
|
|
|
| 99 |
|
| 100 |
-
|
| 101 |
|
| 102 |
-
|
| 103 |
|
| 104 |
-
|
| 105 |
|
| 106 |
-
|
| 107 |
|
| 108 |
-
|
| 109 |
\[
|
| 110 |
</think>
|
| 111 |
|
| 112 |
-
Therefore, the answer is \boxed{
|
| 113 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-kth/math_model`](https://huggingface.co/cs-552-2026-kth/math_model)
|
| 4 |
- **Owner(s):** group **kth**
|
| 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._
|
|
|
|
| 17 |
|
| 18 |
| Benchmark | Accuracy | Status |
|
| 19 |
|---|---:|---|
|
| 20 |
+
| Math | 0.3500 | ok |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `194`
|
| 34 |
+
- **overall** (1/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `194`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
+
## Step 1: Understand the problem
|
| 41 |
+
We need to find the least positive integer $k$ for which we can choose $k$ cells to mark on a $194 \times 194$ board so that there is exactly one tiling of the board by $1 \times 2$ and $2 \times 1$ dominoes in which every domino contains at most one marked cell.
|
| 42 |
|
| 43 |
+
## Step 2: Analyze the tiling condition
|
| 44 |
+
For a $194 \times 194$ board to be tiled by $1 \times
|
| 45 |
|
| 46 |
+
... [truncated 823 chars] ...
|
|
|
|
| 47 |
|
| 48 |
+
Since the board is $194 \times 194$, which is an even number, the minimum $k$ would be related to the number of cells that need to be marked to restrict the possible arrangements of dominoes.
|
|
|
|
| 49 |
|
| 50 |
+
## Step 13: Realize the mistake in the previous step
|
| 51 |
+
The previous step was incorrect because it assumed a specific pattern for marking cells. In reality, the minimum $k$ depends on the specific constraints of the tiling problem and the number of cells that need to be marked to achieve the desired outcome.
|
| 52 |
|
| 53 |
+
## Step 14: Correct the approach
|
| 54 |
+
To solve this problem, we need to consider the constraints imposed by the tiling condition and the requirement for exactly one tiling. This involves finding the minimum number of marked cells required to restrict the possible arrangements of dominoes in a way that meets the given conditions.
|
| 55 |
+
|
| 56 |
+
## Step 15: Consider the solution
|
| 57 |
+
After reevaluating the problem, we realize that the minimum $k$ is related to the size of the board and the constraints imposed by the tiling condition. The correct solution involves finding the minimum number of marked cells required to achieve the desired outcome.
|
| 58 |
+
|
| 59 |
+
The final answer is: $
|
| 60 |
</think>
|
| 61 |
|
| 62 |
+
Therefore, the answer is \boxed{194}.
|
| 63 |
```
|
| 64 |
|
| 65 |
**Incorrect** (1 shown)
|
| 66 |
|
| 67 |
+
- **reference**: `$g(x)=c, g(x)=\lceil x \rceil, g(x)=\lfloor x \rfloor$`
|
| 68 |
- **overall** (0/8 completions correct)
|
| 69 |
+
- **extracted** (✗): `0`
|
| 70 |
- **completion**:
|
| 71 |
|
| 72 |
```text
|
| 73 |
<think>
|
| 74 |
+
Let's use the given functional equation to derive conditions for $h$.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
|
| 76 |
+
Given:
|
| 77 |
+
\[ h(x) = h\left(\frac{h(bx - a) + a}{b}\right) \]
|
| 78 |
|
| 79 |
+
For any $a \in \mathbb{Z}$ and any positive integer $b$, we want to find $h$ that satisfies this equation for all $x \in \mathbb{Q}$.
|
| 80 |
|
| 81 |
+
Substitute $x = 0$ into the given equation:
|
| 82 |
+
\[ h(0) = h\left(\frac{h(-a) + a}{b}\right) \]
|
|
|
|
| 83 |
|
| 84 |
+
Since $h$ maps to $\mathbb{Z}$, $h(-a)$ must also be an integer.
|
| 85 |
|
| 86 |
+
Now, let's consider what happens when we set $a = 0$:
|
| 87 |
+
\[ h(0) = h\left(\frac{h(0)}{b}\right) \]
|
| 88 |
|
| 89 |
+
For this to hold for any $b$, $h(0)$ must be $0$, because otherwise, the right side would not be an integer for all $b$.
|
|
|
|
| 90 |
|
| 91 |
+
So, $h(0) = 0$.
|
| 92 |
|
| 93 |
+
Next, let's examine the case when $b = 1$:
|
| 94 |
+
\[ h(x) = h\left(h(x - a) + a\right) \]
|
| 95 |
|
| 96 |
+
Since $h$ maps to integers and $a$ is an integer, $h(x - a)$ must also be an integer.
|
| 97 |
|
| 98 |
+
However, for the equation to hold for any $x$ and any integer $a$, we must have $h(x) = 0$ for all $x \in \mathbb{Q}$.
|
| 99 |
|
| 100 |
+
This is because if $h(x) \neq 0$ for some $x$, then for any integer $a$, $h(x - a)$ would not be an integer, contradicting the fact that $h$ maps to integers.
|
| 101 |
|
| 102 |
+
Therefore, the only solution is $h(x) = 0$ for all $x \in \mathbb{Q}$.
|
| 103 |
|
| 104 |
+
So, the answer is:
|
| 105 |
\[
|
| 106 |
</think>
|
| 107 |
|
| 108 |
+
Therefore, the answer is \boxed{0}.
|
| 109 |
```
|