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 (2026-05-20)
Browse files- EVAL_REPORT.md +92 -34
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 |
|
|
@@ -24,69 +24,127 @@ _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 |
|
| 36 |
-
|
|
|
|
| 37 |
|
| 38 |
-
|
|
|
|
| 39 |
|
| 40 |
-
|
| 41 |
-
\[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
</think>
|
| 43 |
|
| 44 |
-
Therefore, the answer is \boxed{
|
| 45 |
```
|
| 46 |
|
| 47 |
**Incorrect** (1 shown)
|
| 48 |
|
| 49 |
-
- **reference**: `
|
| 50 |
- **overall** (0/8 completions correct)
|
| 51 |
-
- **extracted** (✗): `
|
| 52 |
- **completion**:
|
| 53 |
|
| 54 |
```text
|
| 55 |
<think>
|
| 56 |
-
Let's
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
-
|
| 59 |
-
\[ h(x) = h\left(\frac{h(bx - a) + a}{b}\right) \]
|
| 60 |
|
| 61 |
-
|
|
|
|
|
|
|
| 62 |
|
| 63 |
-
|
| 64 |
-
\[
|
| 65 |
|
| 66 |
-
|
| 67 |
|
| 68 |
-
Now,
|
|
|
|
| 69 |
|
| 70 |
-
|
| 71 |
|
| 72 |
-
|
| 73 |
-
\[ nx + c = n\left(\frac{n(bx - a) + a + c}{b}\right) + c \]
|
| 74 |
|
| 75 |
-
|
| 76 |
-
\[
|
| 77 |
|
| 78 |
-
|
| 79 |
-
\[
|
| 80 |
|
| 81 |
-
|
| 82 |
|
| 83 |
-
|
| 84 |
|
| 85 |
-
|
| 86 |
|
| 87 |
-
|
| 88 |
-
\[
|
| 89 |
</think>
|
| 90 |
|
| 91 |
-
Therefore, the answer is \boxed{
|
| 92 |
```
|
|
|
|
| 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:** 2026-05-20T05:49:46+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 | 0.2900 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `4`
|
| 28 |
+
- **overall** (1/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `4`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
+
Let's rewrite the given equation as:
|
| 35 |
+
\[ (x^3 - 3x^2 + 3x) + (y^3 - 3y^2 + 3y) + (z^3 - 3z^2 + 3z) = 4 \]
|
| 36 |
|
| 37 |
+
Factor the terms:
|
| 38 |
+
\[ (x - 1)^3 + (y - 1)^3 + (z - 1)^3 = 4 \]
|
| 39 |
|
| 40 |
+
Now, use the fact that for any real numbers $a$, $b$, and $c$:
|
| 41 |
+
\[ a^3 + b^3 + c^3 - 3abc = (a + b + c)(a^2 + b^2 + c^2 - ab - bc - ca) \]
|
| 42 |
|
| 43 |
+
Apply this to our equation:
|
| 44 |
+
\[ (x - 1)^3 + (y - 1)^3 + (z - 1)^3 - 3(x - 1)(y - 1)(z
|
| 45 |
+
|
| 46 |
+
... [truncated 64 chars] ...
|
| 47 |
+
|
| 48 |
+
(x - 1)^2 + (y - 1)^2 + (z - 1)^2 - (x - 1)(y - 1) - (y - 1)(z - 1) - (z - 1)(x - 1)) = 4 \]
|
| 49 |
+
|
| 50 |
+
\[ (x + y + z - 3)((x - 1)^2 + (y - 1)^2 + (z - 1)^2 - (xy - x - y + 1) - (yz - y - z + 1) - (zx - z - x + 1)) = 4 \]
|
| 51 |
+
|
| 52 |
+
\[ (x + y + z - 3)((x - 1)^2 + (y - 1)^2 + (z - 1)^2 - xy - yz - zx + x + y + z - 3) = 4 \]
|
| 53 |
+
|
| 54 |
+
\[ (x + y + z - 3)(x^2 + y^2 + z^2 - 2x - 2y - 2z + 3 - xy - yz - zx + x + y + z - 3) = 4 \]
|
| 55 |
+
|
| 56 |
+
\[ (x + y + z - 3)(x^2 + y^2 + z^2 - xy - yz - zx - x - y - z) = 4 \]
|
| 57 |
+
|
| 58 |
+
Now, we want to find the largest possible value of:
|
| 59 |
+
\[ x^2 + y^2 + z^2 - x - y - z \]
|
| 60 |
+
|
| 61 |
+
Let $a = x + y + z - 3$ and $b = x^2 + y^2 + z^2 - xy - yz - zx$. The equation becomes:
|
| 62 |
+
\[ ab = 4 \]
|
| 63 |
+
|
| 64 |
+
We want to maximize $b$, which is equivalent to minimizing $a$.
|
| 65 |
+
|
| 66 |
+
Since $a$ and $b$ are nonnegative, the minimum value of $a$ is 0, which occurs when $b$ is at its maximum value.
|
| 67 |
+
|
| 68 |
+
When $a = 0$, we have:
|
| 69 |
+
\[ b = 4/a = 4/0 \]
|
| 70 |
+
|
| 71 |
+
However, this is not possible since $b$ cannot be infinity.
|
| 72 |
+
|
| 73 |
+
The next possible value of $a$ is 1, which occurs when $b$ is at its maximum value.
|
| 74 |
+
|
| 75 |
+
When $a = 1$, we have:
|
| 76 |
+
\[ b = 4/a = 4/1 = 4 \]
|
| 77 |
+
|
| 78 |
+
Therefore, the largest possible value of $x^2 + y^2 + z^2 - x - y - z$ is:
|
| 79 |
+
\[
|
| 80 |
</think>
|
| 81 |
|
| 82 |
+
Therefore, the answer is \boxed{4}.
|
| 83 |
```
|
| 84 |
|
| 85 |
**Incorrect** (1 shown)
|
| 86 |
|
| 87 |
+
- **reference**: `(3,2,5)`
|
| 88 |
- **overall** (0/8 completions correct)
|
| 89 |
+
- **extracted** (✗): `\text{None}`
|
| 90 |
- **completion**:
|
| 91 |
|
| 92 |
```text
|
| 93 |
<think>
|
| 94 |
+
Let's start by examining the given conditions:
|
| 95 |
+
|
| 96 |
+
1. \(p\) is a prime greater than 2.
|
| 97 |
+
2. \(m\) and \(n\) are positive integers with \(m \le n\).
|
| 98 |
+
3. \(m^{p-1}+n\) and \(n^{p-1}+m\) are both powers of \(p\).
|
| 99 |
+
|
| 100 |
+
Since \(m^{p-1}+n\) and \(n^{p-1}+m\) are both powers of \(p\), we can write:
|
| 101 |
+
\[ m^{p-1}+n = p^a \]
|
| 102 |
+
\[ n^{p-1}+m = p^b \]
|
| 103 |
+
|
| 104 |
+
where \(a\) and \(b\) are positive integers.
|
| 105 |
+
|
| 106 |
+
Subtracting the tw
|
| 107 |
+
|
| 108 |
+
... [truncated 347 chars] ...
|
| 109 |
+
|
| 110 |
+
f \(a = b\), and the left-hand side is equal to 0.
|
| 111 |
+
|
| 112 |
+
So, we have:
|
| 113 |
+
\[ m^{p-1} - n^{p-1} = 0 \]
|
| 114 |
|
| 115 |
+
This implies that \(m^{p-1} = n^{p-1}\), which means that \(m = n\).
|
|
|
|
| 116 |
|
| 117 |
+
Substituting \(m = n\) into the original equations, we get:
|
| 118 |
+
\[ m^{p-1}+m = p^a \]
|
| 119 |
+
\[ m^{p-1}+m = p^b \]
|
| 120 |
|
| 121 |
+
Since \(m^{p-1}+m\) is a power of \(p\), we can write:
|
| 122 |
+
\[ m^{p-1}+m = p^c \]
|
| 123 |
|
| 124 |
+
where \(c\) is a positive integer.
|
| 125 |
|
| 126 |
+
Now, we can factor out \(m\) from the left-hand side of the equation:
|
| 127 |
+
\[ m(m^{p-2}+1) = p^c \]
|
| 128 |
|
| 129 |
+
Since \(p\) is a prime greater than 2, we know that \(p\) is odd.
|
| 130 |
|
| 131 |
+
Therefore, \(m\) must be a power of \(p\), say \(m = p^d\), where \(d\) is a positive integer.
|
|
|
|
| 132 |
|
| 133 |
+
Substituting \(m = p^d\) into the equation, we get:
|
| 134 |
+
\[ p^d(p^{p-2}+1) = p^c \]
|
| 135 |
|
| 136 |
+
Since \(p^d\) is a power of \(p\), we can cancel out \(p^d\) from both sides of the equation:
|
| 137 |
+
\[ p^{p-2}+1 = p^{c-d} \]
|
| 138 |
|
| 139 |
+
Now, we can see that \(p^{p-2}+1\) is not a power of \(p\), unless \(p-2 = 0\), which means \(p = 2\).
|
| 140 |
|
| 141 |
+
But we are given that \(p\) is a prime greater than 2, so this case is not possible.
|
| 142 |
|
| 143 |
+
Therefore, there are no ordered triples \((p, m, n)\) that satisfy the given conditions.
|
| 144 |
|
| 145 |
+
So, the answer is:
|
| 146 |
+
\[
|
| 147 |
</think>
|
| 148 |
|
| 149 |
+
Therefore, the answer is \boxed{\text{None}}.
|
| 150 |
```
|