Instructions to use cs-552-2026-middle-west/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-middle-west/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-middle-west/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-middle-west/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-middle-west/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-middle-west/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-middle-west/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-middle-west/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-middle-west/math_model
- SGLang
How to use cs-552-2026-middle-west/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-middle-west/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-middle-west/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-middle-west/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-middle-west/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-middle-west/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-middle-west/math_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +93 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-middle-west/math_model`](https://huggingface.co/cs-552-2026-middle-west/math_model)
|
| 4 |
+
- **Owner(s):** group **middle-west**
|
| 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:** [`7d47837`](https://huggingface.co/cs-552-2026-middle-west/math_model/commit/7d4783794c6874ccd12c59b2ce182a1026b24c3d)
|
| 13 |
+
- **Message:** Copy Ilia2003Mah/mnlp_safe_model verbatim to cs-552-2026-middle-west/math_model
|
| 14 |
+
- **Committed:** 2026-06-10T09:04:00+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | 0.5200 | 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**: `6`
|
| 34 |
+
- **overall** (8/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `6`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
Okay, let's see. I need to convert 56 Drinkets into Trinkets. The problem gives me the exchange rates: 1 Trinket is worth 4 Blinkets, and 3 Blinkets are worth 7 Drinkets. So, first, I should figure out how many Blinkets are equivalent to 56 Drinkets, and then convert that number of Blinkets into Trinkets.
|
| 41 |
+
|
| 42 |
+
Starting with the Drinkets to Blinkets conversion. The problem says 3 Blinkets are w
|
| 43 |
+
|
| 44 |
+
... [truncated 823 chars] ...
|
| 45 |
+
|
| 46 |
+
kets divided by 4 is 6 Trinkets. Yes, that seems correct. So the answer should be 6 Trinkets. Let me see if there's another way to approach this.
|
| 47 |
+
|
| 48 |
+
Alternatively, maybe using proportions. Let's set up the conversion factors. The exchange rates can be represented as:
|
| 49 |
+
|
| 50 |
+
Drinkets to Blinkets: 7 Drinkets = 3 Blinkets. So, the ratio is 7:3.
|
| 51 |
+
|
| 52 |
+
Blinkets to Trinkets: 1 Trinket = 4 Blinkets. So, the ratio is 1:4.
|
| 53 |
+
|
| 54 |
+
To convert Drinkets to Trinkets, we can first convert Drinkets to Blinkets, then Blinkets to Trinkets. So, 56 Drinkets * (3 Blinkets / 7 Drinkets) = 24 Blinkets. Then 24 Blinkets * (1 Trinket / 4 Blinkets) = 6 Trinkets. Yep, same result.
|
| 55 |
+
|
| 56 |
+
Another way: Find the overall exchange rate from Drinkets to Trinkets. Let's see. Since 1 Trinket = 4 Blinkets, and 3 Blinkets = 7 Drinkets, then 1 Trinket = 4 * (7/3) Drinkets. Because 3 Blinkets = 7 Drinkets, so 1 Blinket is 7/3 Drinkets. Therefore, 1 Trinket is 4 * (7/3) = 28/3 Drinkets. Therefore, 1 Drinket is 3/28 Trinkets. Therefore, 56 Drinkets is 56 * (3/28) Trinkets. Let's compute that: 56 divided by 28 is 2, multiplied by 3 is 6. So again, 6 Trinkets. So all methods lead to 6. Therefore, the answer should be 6 Trinkets.
|
| 57 |
+
</think>
|
| 58 |
+
|
| 59 |
+
\boxed{6}
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
**Incorrect** (1 shown)
|
| 63 |
+
|
| 64 |
+
- **reference**: `60750, 854130, 854970`
|
| 65 |
+
- **overall** (0/8 completions correct)
|
| 66 |
+
- **extracted** (✗): `60750`
|
| 67 |
+
- **completion**:
|
| 68 |
+
|
| 69 |
+
```text
|
| 70 |
+
<think>
|
| 71 |
+
Okay, let's try to tackle this problem. So we have a function h from natural numbers to natural numbers excluding 1. The condition given is that for every n in natural numbers, h(n) + h(n+1) equals h(n+2) times h(n+3) minus 840. And we need to find all possible values that the sum from i=1 to 2025 of h(i) can take.
|
| 72 |
+
|
| 73 |
+
First, I need to understand the recurrence relation. The equation is h(n)
|
| 74 |
+
|
| 75 |
+
... [truncated 823 chars] ...
|
| 76 |
+
|
| 77 |
+
ry value, I'll list both.
|
| 78 |
+
|
| 79 |
+
But how to represent that in the box? If the system allows multiple answers, but the user's instruction says to put the final answer in a box, I'll have to choose one. But this is not possible. Therefore, I might have made a mistake, and the only possible value is 60,750.
|
| 80 |
+
|
| 81 |
+
But why? Maybe the problem assumes that the function is constant. However, the alternating function is valid.
|
| 82 |
+
|
| 83 |
+
Given the time I've spent and the checks, I'll conclude that both values are possible, and the answer is both. But since I can't put two values in a single box, I'll have to choose one. But this is not correct.
|
| 84 |
+
|
| 85 |
+
Alternatively, maybe the problem has a unique solution, and the other value is not possible. But I can't see why.
|
| 86 |
+
|
| 87 |
+
Given the problem's phrasing, I'll proceed with the two values, and since the user's examples show single answers, perhaps the intended answer is 60,750, and the alternating function is invalid. But I can't justify that.
|
| 88 |
+
|
| 89 |
+
In conclusion, based on the analysis, the possible sums are 60,750 and 854,130. But since I have to choose one, I'll go with the constant function, as it's the only one that's more straightforward, but I'm not sure.
|
| 90 |
+
</think>
|
| 91 |
+
|
| 92 |
+
\boxed{60750}
|
| 93 |
+
```
|