Instructions to use cs-552-2026-vibe-trainers/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-vibe-trainers/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-vibe-trainers/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-vibe-trainers/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-vibe-trainers/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-vibe-trainers/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-vibe-trainers/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-vibe-trainers/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-vibe-trainers/math_model
- SGLang
How to use cs-552-2026-vibe-trainers/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-vibe-trainers/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-vibe-trainers/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-vibe-trainers/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-vibe-trainers/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-vibe-trainers/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-vibe-trainers/math_model
Update Automated MNLP evaluation report (2026-05-27)
Browse files- EVAL_REPORT.md +165 -8
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-vibe-trainers/math_model`](https://huggingface.co/cs-552-2026-vibe-trainers/math_model)
|
| 4 |
- **Owner(s):** group **vibe-trainers**
|
| 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._
|
|
@@ -11,16 +11,173 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
-
| Math |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
| 19 |
-
##
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-vibe-trainers/math_model`](https://huggingface.co/cs-552-2026-vibe-trainers/math_model)
|
| 4 |
- **Owner(s):** group **vibe-trainers**
|
| 5 |
+
- **Generated at:** 2026-05-27T13:02:22+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 | 0.4000 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
| 19 |
+
## Sample completions
|
| 20 |
|
| 21 |
+
_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
|
| 22 |
|
| 23 |
+
### Math
|
| 24 |
+
|
| 25 |
+
**Correct** (1 shown)
|
| 26 |
+
|
| 27 |
+
- **reference**: `194`
|
| 28 |
+
- **overall** (3/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `194`
|
| 30 |
+
- **completion**:
|
| 31 |
+
|
| 32 |
+
```text
|
| 33 |
+
We are given a $194 \times 194$ board and asked to find the **least positive integer $k$** such that we can choose $k$ cells to mark, and there is exactly one tiling of the board by **$1 \times 2$ and $2 \times 1$ dominoes** where **every domino contains at most one marked cell**.
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
### Step 1: Understanding the Problem
|
| 38 |
+
|
| 39 |
+
- The board is $194 \times 194$, so it has $194^2 = 37636$ cells.
|
| 40 |
+
- A dom
|
| 41 |
+
|
| 42 |
+
... [truncated 823 chars] ...
|
| 43 |
+
|
| 44 |
+
ondition that each domino contains at most one marked cell means that **no two marked vertices are connected by an edge**.
|
| 45 |
+
|
| 46 |
+
This is equivalent to saying that the set of marked cells forms an **independent set** in the graph.
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
### Step 4: Tiling and Independent Sets
|
| 51 |
+
|
| 52 |
+
We are told that there is **exactly one** tiling of the board by dominoes with **at most one marked cell per domino**.
|
| 53 |
+
|
| 54 |
+
This means that the **set of marked cells** must be such that:
|
| 55 |
+
- It is an **independent set** (no two marked cells are adjacent).
|
| 56 |
+
- The domino tiling is **unique** (i.e., the tiling is uniquely determined by the set of marked cells).
|
| 57 |
+
|
| 58 |
+
---
|
| 59 |
+
|
| 60 |
+
### Step 5: Minimum Size of Independent Set
|
| 61 |
+
|
| 62 |
+
We are to **minimize** the number of marked cells $k$, such that:
|
| 63 |
+
- The set of marked cells is an **independent set**.
|
| 64 |
+
- The tiling of the board with dominoes is **unique**.
|
| 65 |
+
|
| 66 |
+
This is a **combinatorial optimization** problem.
|
| 67 |
+
|
| 68 |
+
---
|
| 69 |
+
|
| 70 |
+
### Step 6: Known Result
|
| 71 |
+
|
| 72 |
+
This is a classic result in **graph theory** and **domino tiling**. Specifically, the **minimum number of marked cells** needed to ensure a **unique tiling** with **at most one marked cell per domino** is:
|
| 73 |
+
|
| 74 |
+
$$
|
| 75 |
+
\boxed{194}
|
| 76 |
+
$$
|
| 77 |
+
|
| 78 |
+
---
|
| 79 |
+
|
| 80 |
+
### Final Answer
|
| 81 |
+
|
| 82 |
+
$$
|
| 83 |
+
\boxed{194}
|
| 84 |
+
$$
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
**Incorrect** (1 shown)
|
| 88 |
+
|
| 89 |
+
- **reference**: `$g(x)=c, g(x)=\lceil x \rceil, g(x)=\lfloor x \rfloor$`
|
| 90 |
+
- **overall** (0/8 completions correct)
|
| 91 |
+
- **extracted** (✗): `h(x) = c \text{ for some constant } c \in \mathbb{Z}`
|
| 92 |
+
- **completion**:
|
| 93 |
+
|
| 94 |
+
```text
|
| 95 |
+
We are given a functional equation:
|
| 96 |
+
|
| 97 |
+
$$
|
| 98 |
+
h(x) = h\left(\frac{h(bx - a) + a}{b}\right)
|
| 99 |
+
$$
|
| 100 |
+
|
| 101 |
+
for all $ x \in \mathbb{Q} $, $ a \in \mathbb{Z} $, and $ b \in \mathbb{N} $.
|
| 102 |
+
|
| 103 |
+
We are to find all functions $ h : \mathbb{Q} \to \mathbb{Z} $ satisfying this equation.
|
| 104 |
+
|
| 105 |
+
---
|
| 106 |
+
|
| 107 |
+
### Step 1: Analyze the structure of the equation
|
| 108 |
+
|
| 109 |
+
Let’s denote:
|
| 110 |
+
|
| 111 |
+
$$
|
| 112 |
+
y = \frac{h(bx - a) + a}{b}
|
| 113 |
+
$$
|
| 114 |
+
|
| 115 |
+
Then the equation becomes:
|
| 116 |
+
|
| 117 |
+
$$
|
| 118 |
+
h(x)
|
| 119 |
+
|
| 120 |
+
... [truncated 414 chars] ...
|
| 121 |
+
|
| 122 |
+
$, a constant function, for some constant $ c \in \mathbb{Z} $.
|
| 123 |
+
|
| 124 |
+
Then:
|
| 125 |
+
|
| 126 |
+
$$
|
| 127 |
+
h(x) = c, \quad h(bx - a) = c, \quad h\left(\frac{c + a}{b}\right) = c
|
| 128 |
+
$$
|
| 129 |
+
|
| 130 |
+
So the equation becomes:
|
| 131 |
+
|
| 132 |
+
$$
|
| 133 |
+
c = c
|
| 134 |
+
$$
|
| 135 |
+
|
| 136 |
+
This is true for all $ x, a, b $. So **constant functions** are solutions.
|
| 137 |
+
|
| 138 |
+
---
|
| 139 |
+
|
| 140 |
+
### Step 3: Are there non-constant solutions?
|
| 141 |
+
|
| 142 |
+
Suppose $ h $ is not constant. Then there exist $ x_1, x_2 \in \mathbb{Q} $ such that $ h(x_1) \ne h(x_2) $.
|
| 143 |
+
|
| 144 |
+
Let’s test with specific values:
|
| 145 |
+
|
| 146 |
+
#### Try $ x = 1 $, $ a = 1 $, $ b = 1 $
|
| 147 |
+
|
| 148 |
+
Then:
|
| 149 |
+
|
| 150 |
+
$$
|
| 151 |
+
h(1) = h\left(\frac{h(1 - 1) + 1}{1}\right) = h(h(0) + 1)
|
| 152 |
+
$$
|
| 153 |
+
|
| 154 |
+
So:
|
| 155 |
+
|
| 156 |
+
$$
|
| 157 |
+
h(1) = h(h(0) + 1)
|
| 158 |
+
$$
|
| 159 |
+
|
| 160 |
+
If $ h $ is constant, then this is fine. But if $ h $ is not constant, then $ h(0) + 1 $ must be mapped to the same value as $ h(1) $, which may not be possible unless $ h $ is constant.
|
| 161 |
+
|
| 162 |
+
So, **constant functions** are the only possible solutions.
|
| 163 |
+
|
| 164 |
+
---
|
| 165 |
+
|
| 166 |
+
### Step 4: Conclusion
|
| 167 |
+
|
| 168 |
+
The only function $ h : \mathbb{Q} \to \mathbb{Z} $ satisfying the given equation for all $ x, a, b \in \mathbb{Q}, \mathbb{Z}, \mathbb{N} $ is the **constant function**:
|
| 169 |
+
|
| 170 |
+
$$
|
| 171 |
+
\boxed{h(x) = c}
|
| 172 |
+
$$
|
| 173 |
+
|
| 174 |
+
where $ c \in \mathbb{Z} $.
|
| 175 |
+
|
| 176 |
+
---
|
| 177 |
+
|
| 178 |
+
### Final Answer:
|
| 179 |
+
|
| 180 |
+
$$
|
| 181 |
+
\boxed{h(x) = c \text{ for some constant } c \in \mathbb{Z}}
|
| 182 |
+
$$
|
| 183 |
+
```
|