Instructions to use cs-552-2026-baseline/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-baseline/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-baseline/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-baseline/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-baseline/math_model") 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-baseline/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-baseline/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-baseline/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-baseline/math_model
- SGLang
How to use cs-552-2026-baseline/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-baseline/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-baseline/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-baseline/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-baseline/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-baseline/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-baseline/math_model
Automated MNLP evaluation report (2026-06-01)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +161 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-baseline/math_model`](https://huggingface.co/cs-552-2026-baseline/math_model)
|
| 4 |
+
- **Owner(s):** group **baseline**
|
| 5 |
+
- **Generated at:** 2026-06-01T06:13:57+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 |
+
## Summary
|
| 11 |
+
|
| 12 |
+
| Benchmark | Accuracy | Status |
|
| 13 |
+
|---|---:|---|
|
| 14 |
+
| Math | 0.1600 | 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**: `4`
|
| 28 |
+
- **overall** (8/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `4`
|
| 30 |
+
- **completion**:
|
| 31 |
+
|
| 32 |
+
```text
|
| 33 |
+
<think>
|
| 34 |
+
Okay, so I need to solve the equation 10^x minus 10 equals 9990. Let me write that down first: 10^x - 10 = 9990. Hmm, let me think about how to approach this.
|
| 35 |
+
|
| 36 |
+
First, maybe I should isolate the term with the exponent. That means I need to get 10^x by itself on one side of the equation. So, if I add 10 to both sides, that should cancel out the -10 on the left. Let me try that:
|
| 37 |
+
|
| 38 |
+
10^x - 10 +
|
| 39 |
+
|
| 40 |
+
... [truncated 823 chars] ...
|
| 41 |
+
|
| 42 |
+
t the original problem is written as 10^x − 10 = 9990. The way it's written, it's 10^x minus 10, not 10^(x - 10). So unless there's some parentheses I'm missing, but the standard order of operations would make it 10^x - 10.
|
| 43 |
+
|
| 44 |
+
So, yeah, I think that's correct.
|
| 45 |
+
|
| 46 |
+
Another thought: sometimes when dealing with exponents, people might confuse the order of operations. But in this case, since there's no parentheses, it's definitely 10^x minus 10.
|
| 47 |
+
|
| 48 |
+
So, conclusion: x = 4.
|
| 49 |
+
|
| 50 |
+
**Final Answer**
|
| 51 |
+
The solution is \boxed{4}.
|
| 52 |
+
</think>
|
| 53 |
+
|
| 54 |
+
To solve the equation:
|
| 55 |
+
|
| 56 |
+
$$
|
| 57 |
+
10^x - 10 = 9990
|
| 58 |
+
$$
|
| 59 |
+
|
| 60 |
+
---
|
| 61 |
+
|
| 62 |
+
### Step 1: Isolate the Exponential Term
|
| 63 |
+
|
| 64 |
+
We start by isolating the term with the exponent $10^x$:
|
| 65 |
+
|
| 66 |
+
$$
|
| 67 |
+
10^x - 10 = 9990
|
| 68 |
+
$$
|
| 69 |
+
|
| 70 |
+
Add 10 to both sides:
|
| 71 |
+
|
| 72 |
+
$$
|
| 73 |
+
10^x = 9990 + 10 = 10000
|
| 74 |
+
$$
|
| 75 |
+
|
| 76 |
+
---
|
| 77 |
+
|
| 78 |
+
### Step 2: Solve for $x$
|
| 79 |
+
|
| 80 |
+
Now, we need to find the value of $x$ such that:
|
| 81 |
+
|
| 82 |
+
$$
|
| 83 |
+
10^x = 10000
|
| 84 |
+
$$
|
| 85 |
+
|
| 86 |
+
We recognize that:
|
| 87 |
+
|
| 88 |
+
$$
|
| 89 |
+
10^4 = 10000
|
| 90 |
+
$$
|
| 91 |
+
|
| 92 |
+
So, the exponent $x$ must be:
|
| 93 |
+
|
| 94 |
+
$$
|
| 95 |
+
x = 4
|
| 96 |
+
$$
|
| 97 |
+
|
| 98 |
+
---
|
| 99 |
+
|
| 100 |
+
### Step 3: Verify the Solution
|
| 101 |
+
|
| 102 |
+
Substitute $x = 4$ back into the original equation:
|
| 103 |
+
|
| 104 |
+
$$
|
| 105 |
+
10^4 - 10 = 10000 - 10 = 9990
|
| 106 |
+
$$
|
| 107 |
+
|
| 108 |
+
This matches the right-hand side of the equation, confirming that the solution is correct.
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
### Final Answer
|
| 113 |
+
|
| 114 |
+
$$
|
| 115 |
+
\boxed{4}
|
| 116 |
+
$$
|
| 117 |
+
```
|
| 118 |
+
|
| 119 |
+
**Incorrect** (1 shown)
|
| 120 |
+
|
| 121 |
+
- **reference**: `\frac{270}7\text{ degrees}`
|
| 122 |
+
- **overall** (0/8 completions correct)
|
| 123 |
+
- **extracted** (✗): `<no answer>`
|
| 124 |
+
- **completion**:
|
| 125 |
+
|
| 126 |
+
```text
|
| 127 |
+
<think>
|
| 128 |
+
Okay, so I need to find the measure of angle BAC in this figure where there's a square and a regular heptagon sharing the side AD. Let me try to visualize the Asymptote figure first.
|
| 129 |
+
|
| 130 |
+
From the Asymptote code, it seems that there's a regular heptagon and a square sharing the side AD. The square is probably attached to the heptagon along side AD. The points are labeled A, B, C, D, and other
|
| 131 |
+
|
| 132 |
+
... [truncated 823 chars] ...
|
| 133 |
+
|
| 134 |
+
le 360/7°. Therefore, coordinates of B are (-sin(360/7°), -cos(360/7°)).
|
| 135 |
+
|
| 136 |
+
Wait, because cos(180° + α) = -cos(α), sin(180° + α) = -sin(α). So, if α = 360/7°, then coordinates are (-cos(α), -sin(α)).
|
| 137 |
+
|
| 138 |
+
So, coordinates of B: (-cos(360/7°), -sin(360/7°)).
|
| 139 |
+
|
| 140 |
+
So, now we have coordinates for points A, B, C.
|
| 141 |
+
|
| 142 |
+
Point A: (-sin(3θ), cos(4θ)) where θ = 360/7°.
|
| 143 |
+
|
| 144 |
+
Point B: (-cos(α), -sin(α)) where α = 360/7°.
|
| 145 |
+
|
| 146 |
+
Point C: (-sin(3θ), cos(4θ)).
|
| 147 |
+
|
| 148 |
+
Wait, hold on. Wait, point C is at (-sin(3θ), cos(4θ)), and point A is at (-sin(3θ), cos(4θ))? Wait, no. Wait, earlier I said point C is at (-sin(3θ), cos(4θ)), but point A is at (-sin(3θ), cos(3θ))? Wait, no. Wait, let me check again.
|
| 149 |
+
|
| 150 |
+
Earlier, coordinates of A: (-sin(3θ), cos(3θ)) where θ = 360/7°, right? Because angle of A is 90° + 3θ, which is 90° + 3*(360/7°). Then, coordinates of A are (cos(90° + 3θ), sin(90° + 3θ)) which is (-sin(3θ), cos(3θ)).
|
| 151 |
+
|
| 152 |
+
Similarly, coordinates of point C: (-sin(3θ), cos(4θ)).
|
| 153 |
+
|
| 154 |
+
So, point A and point C have the same x-coordinate: -sin(3θ), but different y-coordinates: cos(3θ) and cos(4θ).
|
| 155 |
+
|
| 156 |
+
Point B is at (-cos(α), -sin(α)) where α = 360/7°.
|
| 157 |
+
|
| 158 |
+
So, to find angle BAC, which is the angle at point A between points B, A, and C.
|
| 159 |
+
|
| 160 |
+
So, angle B
|
| 161 |
+
```
|