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
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +131 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 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:** 2026-06-11T06:23:10+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:** [`f3af117`](https://huggingface.co/cs-552-2026-kth/math_model/commit/f3af117f54f6320d85a2714fdd5565d50205e7ad)
|
| 13 |
+
- **Message:** Upload tokenizer
|
| 14 |
+
- **Committed:** 2026-05-28T17:08:49+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | 0.3300 | 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{1}{21}`
|
| 34 |
+
- **overall** (4/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `-\frac{1}{21}`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
The equation of the curve is \(y = x^2 + \frac{2}{x}\). The straight line intersects this curve at three distinct points.
|
| 41 |
+
|
| 42 |
+
Let the equation of the line be \(y = mx + b\), where \(m\) is the slope and \(b\) is the y-intercept.
|
| 43 |
+
|
| 44 |
+
Substitute \(y = mx + b\) into the equation of the curve:
|
| 45 |
+
\[ mx + b = x^2 + \frac{2}{x} \Rightarrow x^2 - mx - \frac{2}{x} - b = 0 \]
|
| 46 |
+
|
| 47 |
+
Since two of the intersection
|
| 48 |
+
|
| 49 |
+
... [truncated 823 chars] ...
|
| 50 |
+
|
| 51 |
+
}\) into (1) to find \(b\):
|
| 52 |
+
\[ -6\left(\frac{286}{21}\right) - b = -\frac{107}{3} \Rightarrow -\frac{1716}{21} - b = -\frac{107}{3} \Rightarrow b = -\frac{107}{3} + \frac{1716}{21} \Rightarrow b = \frac{-107 \cdot 7 + 1716}{21} \Rightarrow b = \frac{-749 + 1716}{21} \Rightarrow b = \frac{967}{21} \]
|
| 53 |
+
|
| 54 |
+
Now that we have \(m = \frac{286}{21}\) and \(b = \frac{967}{21}\), we can substitute these values into the equation of the line:
|
| 55 |
+
\[ y = \frac{286}{21}x + \frac{967}{21} \]
|
| 56 |
+
|
| 57 |
+
To find the \(x\)-coordinate of the remaining point, substitute \(y = mx + b\) into the equation of the curve:
|
| 58 |
+
\[ \frac{286}{21}x + \frac{967}{21} = x^2 + \frac{2}{x} \Rightarrow x^2 - \frac{286}{21}x - \frac{2}{x} - \frac{967}{21} = 0 \]
|
| 59 |
+
|
| 60 |
+
Multiply through by \(21x\) to clear the fractions:
|
| 61 |
+
\[ 21x^3 - 286x^2 - 42 - 967x = 0 \Rightarrow 21x^3 - 286x^2 - 967x - 42 = 0 \]
|
| 62 |
+
|
| 63 |
+
Since \(x = 6\) and \(x = 7\) are solutions, we can factor out \((x - 6)\) and \((x - 7)\) from the equation:
|
| 64 |
+
\[ (x - 6)(x - 7)(21x + 1) = 0 \]
|
| 65 |
+
|
| 66 |
+
This gives us the possible values of \(x\): \(x = 6\), \(x = 7\), and \(x = -\frac{1}{21}\).
|
| 67 |
+
|
| 68 |
+
So, the \(x\)-coordinate of the remaining point is:
|
| 69 |
+
\[
|
| 70 |
+
</think>
|
| 71 |
+
|
| 72 |
+
Therefore, the answer is \boxed{-\frac{1}{21}}.
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
**Incorrect** (1 shown)
|
| 76 |
+
|
| 77 |
+
- **reference**: `756`
|
| 78 |
+
- **overall** (0/8 completions correct)
|
| 79 |
+
- **extracted** (✗): `100`
|
| 80 |
+
- **completion**:
|
| 81 |
+
|
| 82 |
+
```text
|
| 83 |
+
<think>
|
| 84 |
+
We know that the distance between the centers of the two balloons is equal to the sum of their radii. Let's denote the centers of the balloons with radii $11$, $13$, and $19$ as $A$, $B$, and $C$ respectively. Then, we have:
|
| 85 |
+
|
| 86 |
+
\[ AB = 11 + 13 = 24 \]
|
| 87 |
+
\[ BC = 13 + 19 = 32 \]
|
| 88 |
+
\[ AC = 11 + 19 = 30 \]
|
| 89 |
+
|
| 90 |
+
Since the centers of the balloons lie on one side of the plane, the triangle $ABC$ is a trian
|
| 91 |
+
|
| 92 |
+
... [truncated 34 chars] ...
|
| 93 |
+
|
| 94 |
+
$. We can use Heron's formula to find the area of the triangle $ABC$:
|
| 95 |
+
|
| 96 |
+
\[ s = \frac{24 + 32 + 30}{2} = 43 \]
|
| 97 |
+
\[ \text{Area} = \sqrt{s(s - 24)(s - 32)(s - 30)} = \sqrt{43 \cdot 19 \cdot 11 \cdot 13} = 43 \cdot 11 \cdot \sqrt{13} \]
|
| 98 |
+
|
| 99 |
+
Now, we need to find the area of the triangle $XYZ$. Since the plane cuts the balloons in three congruent circular cross-sections, the triangle $XYZ$ is similar to the triangle $ABC$. Let's denote the distance between the centers $X$ and $Z$ as $d$. Then, we have:
|
| 100 |
+
|
| 101 |
+
\[ XY = \frac{24}{3} = 8 \]
|
| 102 |
+
\[ YZ = \frac{32}{3} \]
|
| 103 |
+
\[ XZ = d \]
|
| 104 |
+
|
| 105 |
+
Using the similarity of the triangles, we can write:
|
| 106 |
+
|
| 107 |
+
\[ \frac{XY}{AB} = \frac{YZ}{BC} = \frac{XZ}{AC} \]
|
| 108 |
+
|
| 109 |
+
Substituting the values, we get:
|
| 110 |
+
|
| 111 |
+
\[ \frac{8}{24} = \frac{\frac{32}{3}}{32} = \frac{d}{30} \]
|
| 112 |
+
|
| 113 |
+
Simplifying, we get:
|
| 114 |
+
|
| 115 |
+
\[ \frac{1}{3} = \frac{1}{3} = \frac{d}{30} \]
|
| 116 |
+
|
| 117 |
+
Solving for $d$, we get:
|
| 118 |
+
|
| 119 |
+
\[ d = 30 \cdot \frac{1}{3} = 10 \]
|
| 120 |
+
|
| 121 |
+
Now, we can find the area of the triangle $XYZ$:
|
| 122 |
+
|
| 123 |
+
\[ \text{Area}_{XYZ} = \frac{1}{3} \cdot \text{Area}_{ABC} = \frac{1}{3} \cdot 43 \cdot 11 \cdot \sqrt{13} = \frac{43 \cdot 11}{3} \cdot \sqrt{13} \]
|
| 124 |
+
|
| 125 |
+
Finally, we can find $XZ^2$:
|
| 126 |
+
|
| 127 |
+
\[ XZ^2 = d^2 = 10^2 =
|
| 128 |
+
</think>
|
| 129 |
+
|
| 130 |
+
Therefore, the answer is \boxed{100}.
|
| 131 |
+
```
|