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 (2026-06-10)
Browse files- EVAL_REPORT.md +36 -19
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 |
|
|
@@ -30,36 +30,53 @@ _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 |
-
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 |
-
|
| 44 |
-
For a $194 \times 194$ board to be tiled by $1 \times
|
| 45 |
|
| 46 |
-
|
| 47 |
|
| 48 |
-
|
| 49 |
|
| 50 |
-
|
| 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 |
-
|
| 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 |
-
|
| 57 |
-
|
| 58 |
|
| 59 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
</think>
|
| 61 |
|
| 62 |
-
Therefore, the answer is \boxed{
|
| 63 |
```
|
| 64 |
|
| 65 |
**Incorrect** (1 shown)
|
|
|
|
| 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:** 2026-06-10T21:20:55+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 | 0.3400 | ok |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `\frac{7}{4}`
|
| 34 |
+
- **overall** (6/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `\frac{7}{4}`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
+
To find the value of $b$, we need to use the fact that the red line is parametrized with a direction vector of the form $\begin{pmatrix} -7 \\ b \end{pmatrix}$.
|
|
|
|
| 41 |
|
| 42 |
+
The direction vector of the red line is $\begin{pmatrix} -7 \\ b \end{pmatrix}$.
|
|
|
|
| 43 |
|
| 44 |
+
Since the red line is parametrized with a direction vector of the form $\begin{pmatrix} -7 \\ b \end{pmatrix}$, we can write the equation of the red
|
| 45 |
|
| 46 |
+
... [truncated 391 chars] ...
|
| 47 |
|
| 48 |
+
= \frac{\begin{pmatrix} -5 \\ 4 \end{pmatrix}}{\begin{pmatrix} -7 \\ b \end{pmatrix}} \]
|
|
|
|
| 49 |
|
| 50 |
+
Since $t$ is a parameter, it must be a constant value.
|
|
|
|
| 51 |
|
| 52 |
+
Equating the two expressions for $t$, we get:
|
| 53 |
+
\[ \frac{\begin{pmatrix} -5 \\ 4 \end{pmatrix}}{\begin{pmatrix} -7 \\ b \end{pmatrix}} = \frac{\begin{pmatrix} -1 \\ 3 \end{pmatrix}}{\begin{pmatrix} -7 \\ b \end{pmatrix}} \]
|
| 54 |
|
| 55 |
+
Comparing the two expressions, we get:
|
| 56 |
+
\[ \frac{-5}{-7} = \frac{-1}{-7} \quad \text{and} \quad \frac{4}{b} = \frac{3}{b} \]
|
| 57 |
+
|
| 58 |
+
Simplifying, we get:
|
| 59 |
+
\[ \frac{5}{7} = \frac{1}{7} \quad \text{and} \quad 4 = 3 \]
|
| 60 |
+
|
| 61 |
+
The first equation is not true, so there is no value of $b$ that satisfies the equation.
|
| 62 |
+
|
| 63 |
+
However, the second equation is not true either, so there is no value of $b$ that satisfies the equation.
|
| 64 |
+
|
| 65 |
+
But, we can see that the red line passes through the points $(-5,4)$ and $(-1,3)$.
|
| 66 |
+
|
| 67 |
+
The slope of the red line is:
|
| 68 |
+
\[ \frac{4 - 3}{-5 - (-1)} = \frac{1}{-4} = -\frac{1}{4} \]
|
| 69 |
+
|
| 70 |
+
The slope of the red line is also equal to $\frac{b}{-7}$.
|
| 71 |
+
|
| 72 |
+
Equating the two expressions for the slope, we get:
|
| 73 |
+
\[ \frac{b}{-7} = -\frac{1}{4} \]
|
| 74 |
+
|
| 75 |
+
Solving for $b$, we get:
|
| 76 |
+
\[ b = \frac{-7}{-4} =
|
| 77 |
</think>
|
| 78 |
|
| 79 |
+
Therefore, the answer is \boxed{\frac{7}{4}}.
|
| 80 |
```
|
| 81 |
|
| 82 |
**Incorrect** (1 shown)
|