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 (2026-05-18)
Browse files- EVAL_REPORT.md +46 -42
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:** 2026-05-
|
| 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 |
|
|
@@ -24,66 +24,70 @@ _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 |
-
|
| 35 |
-
\[ 10^x = 10 + 9990 \Rightarrow 10^x = 10000 \Rightarrow 10^x = 10^4 \]
|
| 36 |
|
| 37 |
-
Since
|
| 38 |
-
\[ x = 4 \]
|
| 39 |
|
| 40 |
-
|
| 41 |
-
\[
|
| 42 |
-
</think>
|
| 43 |
-
|
| 44 |
-
Therefore, the answer is \boxed{4}.
|
| 45 |
-
```
|
| 46 |
-
|
| 47 |
-
**Incorrect** (1 shown)
|
| 48 |
-
|
| 49 |
-
- **reference**: `2 - \frac{\pi}{2}`
|
| 50 |
-
- **overall** (0/8 completions correct)
|
| 51 |
-
- **extracted** (✗): `\frac{1}{2}`
|
| 52 |
-
- **completion**:
|
| 53 |
-
|
| 54 |
-
```text
|
| 55 |
-
<think>
|
| 56 |
-
Let $P$ be the probability that Derek eventually becomes debt-free. We can derive a recursive equation for $P$.
|
| 57 |
|
| 58 |
-
|
| 59 |
|
| 60 |
-
|
| 61 |
-
2. Tails: He reduces his debt by 2 MITs. This means his debt becomes $\pi - 2$ MITs.
|
| 62 |
|
| 63 |
-
|
| 64 |
|
| 65 |
-
|
| 66 |
|
| 67 |
-
|
| 68 |
|
| 69 |
-
|
| 70 |
|
| 71 |
-
\
|
| 72 |
|
| 73 |
-
|
| 74 |
|
| 75 |
-
|
| 76 |
|
| 77 |
-
|
| 78 |
|
| 79 |
-
|
| 80 |
|
| 81 |
-
\
|
| 82 |
|
| 83 |
-
|
|
|
|
| 84 |
|
| 85 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
</think>
|
| 87 |
|
| 88 |
-
Therefore, the answer is \boxed{
|
| 89 |
```
|
|
|
|
| 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:** 2026-05-18T02:30:25+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 | 0.3200 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `$\frac{a}{2}$`
|
| 28 |
+
- **overall** (2/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `\frac{a}{2}`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
+
Since \(P\) is the circumcenter of triangle \(XYZ\), \(P\) is equidistant from the vertices \(X\), \(Y\), and \(Z\). Therefore, \(PX = PY = PZ\).
|
|
|
|
| 35 |
|
| 36 |
+
Since \(Q\) is the midpoint of \(YZ\), \(Q\) is also the midpoint of \(XY\), because \(XY = XZ\).
|
|
|
|
| 37 |
|
| 38 |
+
When \(R\) is the image of \(Q\) after reflection across the side \(XZ\), \(R\) is on the line \(XY\), and \(QR = XZ = XY\).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
+
Since \(XQYS\) is a rectangle, \(XQ = QS = YS\).
|
| 41 |
|
| 42 |
+
Since \(Q\) is the midpoint of \(YZ\), \(QY = QZ\).
|
|
|
|
| 43 |
|
| 44 |
+
Since \(R\) is on the line \(XY\), \(QR\) is perpendicular to \(XZ\).
|
| 45 |
|
| 46 |
+
Since \(XQYS\) is a rectangle, \(XQ\) is perpendicular to \(YS\).
|
| 47 |
|
| 48 |
+
Since \(QY = QZ\), and \(XQ = QS\), we have \(XQ = QY\).
|
| 49 |
|
| 50 |
+
Therefore, triangle \(XQY\) is a right triangle.
|
| 51 |
|
| 52 |
+
Since \(\angle YXZ = a\), we have \(\angle QXY = 90^\circ - a\).
|
| 53 |
|
| 54 |
+
Since \(XQYS\) is a rectangle, \(\angle QYS = 90^\circ\).
|
| 55 |
|
| 56 |
+
Since \(QR\) is perpendicular to \(XZ\), \(\angle QRS = 90^\circ\).
|
| 57 |
|
| 58 |
+
Since \(XQ = QS\), triangle \(QXS\) is isosceles.
|
| 59 |
|
| 60 |
+
Therefore, \(\angle QXS = \angle QSX = 90^\circ - \frac{a}{2}\).
|
| 61 |
|
| 62 |
+
Since \(\angle QRS = 90^\circ\), we have \(\angle PRS = 180^\circ - \angle QRS - \angle QXS = 180^\circ - 90^\circ - (90^\circ - \frac{a}{2}) = \frac{a}{2}\).
|
| 63 |
|
| 64 |
+
Therefore, \(\angle PRS =
|
| 65 |
+
</think>
|
| 66 |
|
| 67 |
+
Therefore, the answer is \boxed{\frac{a}{2}}.
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
**Incorrect** (1 shown)
|
| 71 |
+
|
| 72 |
+
- **reference**: `104`
|
| 73 |
+
- **overall** (0/8 completions correct)
|
| 74 |
+
- **extracted** (✗): `51`
|
| 75 |
+
- **completion**:
|
| 76 |
+
|
| 77 |
+
```text
|
| 78 |
+
<think>
|
| 79 |
+
## Step 1: To solve this problem, we first need to understand the given tetrahedron $WXYZ$ and the conditions for point $P$ being equidistant from all four faces.
|
| 80 |
+
## Step 2: The tetrahedron $WXYZ$ has edge lengths $WX = YZ = \sqrt{41}$, $WY = XZ = \sqrt{80}$, and $WZ = XY = \sqrt{89}$.
|
| 81 |
+
## Step 3: We are given that point $P$ lies inside the tetrahedron and is equidistant from all four of its faces. This common distance is denoted as $d$.
|
| 82 |
+
## Step 4: To find the value of $d$, we can use the properties of the tetrahedron and the given edge lengths.
|
| 83 |
+
## Step 5: We can start by finding the area of the triangle $XYZ$. Using Heron's formula, we can calculate the area as $\frac{1}{2}\sqrt{41\cdot89\cdot80}$.
|
| 84 |
+
## Step 6: Then, we can find the volume of the tetrahedron $WXYZ$ using the formula $\frac{1}{3}\cdot(\text{area of base})\cdot\text{height}$. The height is the distance from point $W$ to the plane containing the base $XYZ$.
|
| 85 |
+
## Step 7: We can then use the formula for the volume of a tetrahedron to express the volume in terms of the distance $d$ and the areas of the faces.
|
| 86 |
+
## Step 8: By equating the two expressions for the volume, we can solve for the value of $d$.
|
| 87 |
+
## Step 9: Finally, we can express the common distance $d$ in the form $\frac{a\sqrt{b}}{c}$ and calculate the sum $a+b+c$.
|
| 88 |
+
|
| 89 |
+
The final answer is: $
|
| 90 |
</think>
|
| 91 |
|
| 92 |
+
Therefore, the answer is \boxed{51}.
|
| 93 |
```
|