Instructions to use cs-552-2026-painlp/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-painlp/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-painlp/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-painlp/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-painlp/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-painlp/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-painlp/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-painlp/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-painlp/math_model
- SGLang
How to use cs-552-2026-painlp/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-painlp/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-painlp/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-painlp/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-painlp/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-painlp/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-painlp/math_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +92 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-painlp/math_model`](https://huggingface.co/cs-552-2026-painlp/math_model)
|
| 4 |
+
- **Owner(s):** group **painlp**
|
| 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:** [`97762f0`](https://huggingface.co/cs-552-2026-painlp/math_model/commit/97762f02e2ae010a19fe54c26600f0fc92c4d9af)
|
| 13 |
+
- **Message:** upload: generation_config
|
| 14 |
+
- **Committed:** 2026-05-24T16:28:57+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | 0.3100 | 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**: `4`
|
| 34 |
+
- **overall** (8/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `4`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
To solve for $x$ in the equation $10^x - 10 = 9990$, we can start by isolating the term $10^x$.
|
| 41 |
+
|
| 42 |
+
1. Add 10 to both sides of the equation:
|
| 43 |
+
\[ 10^x = 9990 + 10 \Rightarrow 10^x = 10000 \]
|
| 44 |
+
|
| 45 |
+
2. Recognize that $10000 = 10^4$, so we have:
|
| 46 |
+
\[ 10^x = 10^4 \]
|
| 47 |
+
|
| 48 |
+
3. Since the bases are the same, we can equate the exponents:
|
| 49 |
+
\[ x = 4 \]
|
| 50 |
+
|
| 51 |
+
Thus, the solution is:
|
| 52 |
+
\[
|
| 53 |
+
</think>
|
| 54 |
+
|
| 55 |
+
\boxed{4} \]
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
**Incorrect** (1 shown)
|
| 59 |
+
|
| 60 |
+
- **reference**: `2 - \frac{\pi}{2}`
|
| 61 |
+
- **overall** (0/8 completions correct)
|
| 62 |
+
- **extracted** (✗): `<no answer>`
|
| 63 |
+
- **completion**:
|
| 64 |
+
|
| 65 |
+
```text
|
| 66 |
+
<think>
|
| 67 |
+
Okay, so Derek starts with a debt of π MIT, which is approximately 3.1416 MIT. Each day, he tosses a fair coin: heads reduces his debt by 1 MIT, tails by 2 MITs. If his debt ever becomes nonpositive, he's debt-free. Otherwise, after paying, his debt is doubled. We need to find the probability that Derek eventually becomes debt-free. Hmm, interesting problem. Let me try to break this down.
|
| 68 |
+
|
| 69 |
+
... [truncated 823 chars] ...
|
| 70 |
+
|
| 71 |
+
P(0) = 1/2 * 1/2 + 1/2 * 1 = 3/4. But earlier, we thought P(2) = 1/2. This is a contradiction.
|
| 72 |
+
|
| 73 |
+
Wait, this suggests that our earlier calculation was wrong. Let's re-examine.
|
| 74 |
+
|
| 75 |
+
When x = 2, paying 1 MIT leads to 1 MIT, which is positive, so P(2) = 1/2 * P(1) + 1/2 * P(0). P(1) = 1/2, P(0) = 1. So P(2) = 1/2 * 1/2 + 1/2 * 1 = 3/4. But earlier, we thought P(2) = 1/2. This is a mistake! Earlier, I incorrectly stated that P(2) = 1/2, but actually, it should be 3/4. This changes everything!
|
| 76 |
+
|
| 77 |
+
Let's recalculate the earlier terms with this correction.
|
| 78 |
+
|
| 79 |
+
x = 1: P(1) = 1/2
|
| 80 |
+
|
| 81 |
+
x = 2: P(2) = 1/2 * P(1) + 1/2 * P(0) = 1/2 * 1/2 + 1/2 * 1 = 3/4
|
| 82 |
+
|
| 83 |
+
x = 3: P(3) = 1/2 * P(2) + 1/2 * P(2(x - 2)) = 1/2 * 3/4 + 1/2 * P(2) = 3/8 + 1/2 * 3/4 = 3/8 + 3/8 = 6/8 = 3/4
|
| 84 |
+
|
| 85 |
+
x = 4: P(4) = 1/2 * P(3) + 1/2 * P(2(x - 2)) = 1/2 * 3/4 + 1/2 * P(2) = 3/8 + 1/2 * 3/4 = 3/8 + 3/8 = 6/8 = 3/4
|
| 86 |
+
|
| 87 |
+
x = 5: P(5) = 1/2 * P(4) + 1/2 * P(2(x - 2)) = 1/2 * 3/4 + 1/2 * P(2) = 3/8 + 3/8 = 6/8 = 3/4
|
| 88 |
+
|
| 89 |
+
Wait, this can't be right. All P(x) from x = 2 onwards are 3/4? That doesn't make sense. Let's check:
|
| 90 |
+
|
| 91 |
+
Wait, no, x = 5: P(5) = 1/2 * P(4) + 1/2 * P(2(5 - 2)) = 1/2 * 3/4 + 1/2 * P(6) = 3/8 + 1/2 * P(6). But P(6) = 1/2 * P(4) + 1/2 * P(4) = 1/2 *
|
| 92 |
+
```
|