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 (2026-06-06)
Browse files- EVAL_REPORT.md +66 -68
EVAL_REPORT.md
CHANGED
|
@@ -2,16 +2,22 @@
|
|
| 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._
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
## Summary
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
-
| Math | 0.
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
@@ -24,92 +30,84 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
-
- **overall** (
|
| 29 |
-
- **extracted** (✓): `\frac{
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
-
|
| 35 |
-
We are given an isosceles triangle \(XYZ\) with \(XY = XZ\), and \(P\) is its circumcenter. We also have \(Q\) as the midpoint of \(YZ\) and \(R\) as the image of \(Q\) after reflection across the side \(XZ\). Additionally, \(S\) is a point chosen such that the quadrilateral \(XQYS\) is a rectangle.
|
| 36 |
-
|
| 37 |
-
## Step 2: Determine the properties of the circumcenter \(P\) and its relation to the triangle \(XYZ\).
|
| 38 |
-
Since \(P\) is the circumcenter of \(XYZ\), it is equidistant from the vertices \(X\), \(Y\), and \(Z\). This implies that \(PX = PY = PZ\).
|
| 39 |
|
| 40 |
-
|
| 41 |
-
|
| 42 |
|
| 43 |
-
|
| 44 |
-
|
| 45 |
|
| 46 |
-
|
| 47 |
-
|
| 48 |
|
| 49 |
-
|
| 50 |
-
|
| 51 |
|
| 52 |
-
The
|
|
|
|
| 53 |
</think>
|
| 54 |
|
| 55 |
-
Therefore, the answer is \boxed{\frac{
|
| 56 |
```
|
| 57 |
|
| 58 |
**Incorrect** (1 shown)
|
| 59 |
|
| 60 |
-
- **reference**: `
|
| 61 |
- **overall** (0/8 completions correct)
|
| 62 |
-
- **extracted** (✗): `
|
| 63 |
- **completion**:
|
| 64 |
|
| 65 |
```text
|
| 66 |
<think>
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
\
|
| 70 |
-
\
|
| 71 |
-
\
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
\[
|
| 83 |
-
\[
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
\[
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
\
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
\[
|
| 107 |
-
\[ XZ^2 = \frac{15297600 - 1716923}{3240} \]
|
| 108 |
-
\[ XZ^2 = \frac{13580677}{3240} \]
|
| 109 |
-
\[ XZ^2 = \frac{13580677}{3240} \]
|
| 110 |
-
\[ XZ^2 = 4180.42 \]
|
| 111 |
-
\[ XZ^2 =
|
| 112 |
</think>
|
| 113 |
|
| 114 |
-
Therefore, the answer is \boxed{
|
| 115 |
```
|
|
|
|
| 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:** 2026-06-06T17:20:53+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 | 0.2800 | ok |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
| Multilingual | — | not run |
|
| 23 |
| Safety | — | not run |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `\frac{14}{3}`
|
| 34 |
+
- **overall** (8/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `\frac{14}{3}`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
+
We can compute each value of \(f(x)\) separately and then add them together.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
+
1. Compute \(f(-2)\):
|
| 43 |
+
\[ f(-2) = \frac{3(-2) - 2}{-2 - 2} = \frac{-6 - 2}{-4} = \frac{-8}{-4} = 2 \]
|
| 44 |
|
| 45 |
+
2. Compute \(f(-1)\):
|
| 46 |
+
\[ f(-1) = \frac{3(-1) - 2}{-1 - 2} = \frac{-3 - 2}{-3} = \frac{-5}{-3} = \frac{5}{3} \]
|
| 47 |
|
| 48 |
+
3. Compute \(f(0)\):
|
| 49 |
+
\[ f(0) = \frac{3(0) - 2}{0 - 2} = \frac{0 - 2}{-2} = \frac{-2}{-2} = 1 \]
|
| 50 |
|
| 51 |
+
Now add these values together:
|
| 52 |
+
\[ f(-2) + f(-1) + f(0) = 2 + \frac{5}{3} + 1 = \frac{6}{3} + \frac{5}{3} + \frac{3}{3} = \frac{14}{3} \]
|
| 53 |
|
| 54 |
+
The answer is:
|
| 55 |
+
\[
|
| 56 |
</think>
|
| 57 |
|
| 58 |
+
Therefore, the answer is \boxed{\frac{14}{3}}.
|
| 59 |
```
|
| 60 |
|
| 61 |
**Incorrect** (1 shown)
|
| 62 |
|
| 63 |
+
- **reference**: `(3,2,5)`
|
| 64 |
- **overall** (0/8 completions correct)
|
| 65 |
+
- **extracted** (✗): `\text{None}`
|
| 66 |
- **completion**:
|
| 67 |
|
| 68 |
```text
|
| 69 |
<think>
|
| 70 |
+
Let's start by examining the given conditions:
|
| 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 |
+
... [truncated 526 chars] ...
|
| 81 |
+
|
| 82 |
+
p > 3\).
|
| 83 |
+
|
| 84 |
+
We can rewrite the given conditions as:
|
| 85 |
+
\[ m^{p-1}+n = a^{p} \]
|
| 86 |
+
\[ n^{p-1}+m = b^{p} \]
|
| 87 |
+
|
| 88 |
+
where \(a\) and \(b\) are positive integers.
|
| 89 |
+
|
| 90 |
+
Subtracting the two equations, we get:
|
| 91 |
+
\[ m^{p-1}-n^{p-1} = a^{p}-b^{p} \]
|
| 92 |
+
|
| 93 |
+
Using the fact that \(p\) is a prime greater than 2, we can factor the left-hand side of the equation as:
|
| 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 |
+
Since \(m \le n\), we have \(m-n \le 0\). Therefore, the left-hand side of the equation is non-positive.
|
| 97 |
+
|
| 98 |
+
On the other hand, the right-hand side of the equation is non-negative, since \(a \ge b\) and \(a^{p-1}+a^{p-2}b+\cdots+ab^{p-2} \ge 0\).
|
| 99 |
+
|
| 100 |
+
This is a contradiction, since the left-hand side of the equation is non-positive and the right-hand side of the equation is non-negative.
|
| 101 |
+
|
| 102 |
+
Therefore, our assumption that there exists an ordered triple \((m, n)\) such that \(m^{p-1}+n\) and \(n^{p-1}+m\) are both powers of \(p\), and \(p > 3\), is false.
|
| 103 |
+
|
| 104 |
+
Hence, there are no solutions for \(p > 3\).
|
| 105 |
+
|
| 106 |
+
In conclusion, the only possible value of \(p\) is 3, and there are no solutions for \(p = 3\).
|
| 107 |
+
|
| 108 |
+
Therefore, the final answer is:
|
| 109 |
+
\[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
</think>
|
| 111 |
|
| 112 |
+
Therefore, the answer is \boxed{\text{None}}.
|
| 113 |
```
|