Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use cs-552-2026-MandMP/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-MandMP/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-MandMP/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-MandMP/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-MandMP/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-MandMP/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-MandMP/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-MandMP/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-MandMP/math_model
- SGLang
How to use cs-552-2026-MandMP/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-MandMP/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-MandMP/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-MandMP/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-MandMP/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-MandMP/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-MandMP/math_model
Automated MNLP evaluation report (2026-05-27)
Browse files- EVAL_REPORT.md +25 -27
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MandMP/math_model`](https://huggingface.co/cs-552-2026-MandMP/math_model)
|
| 4 |
- **Owner(s):** group **MandMP**
|
| 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 |
|
|
@@ -24,60 +24,58 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
- **overall** (8/8 completions correct)
|
| 29 |
-
- **extracted** (✓): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
-
Okay, so
|
| 34 |
|
| 35 |
-
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
-
|
| 40 |
|
| 41 |
-
|
| 42 |
|
| 43 |
-
|
| 44 |
|
| 45 |
-
|
| 46 |
|
| 47 |
-
|
|
|
|
|
|
|
| 48 |
|
| 49 |
**Final Answer**
|
| 50 |
-
|
| 51 |
</think>
|
| 52 |
|
| 53 |
-
\boxed{
|
| 54 |
```
|
| 55 |
|
| 56 |
**Incorrect** (1 shown)
|
| 57 |
|
| 58 |
-
- **reference**: `
|
| 59 |
- **overall** (0/8 completions correct)
|
| 60 |
- **extracted** (✗): `<no answer>`
|
| 61 |
- **completion**:
|
| 62 |
|
| 63 |
```text
|
| 64 |
-
Okay, so I need to solve this
|
| 65 |
-
|
| 66 |
-
First, we have a tetrahedron $ T_1T_2T_3T_4 $ in 3D space. There's a point $ C $ such that its distance to all four vertices is equal. So, $ CT_1 = CT_2 = CT_3 = CT_4 $. That means $ C $ is equidistant from all four vertices of the tetrahedron.
|
| 67 |
|
| 68 |
-
|
| 69 |
|
| 70 |
-
... [truncated
|
| 71 |
-
|
| 72 |
-
,-1,1), C(-1,1,-1), D(1,-1,-1). Let me find the equation of the plane through these three points.
|
| 73 |
|
| 74 |
-
|
| 75 |
|
| 76 |
-
|
| 77 |
|
| 78 |
-
|
| 79 |
|
| 80 |
-
|
| 81 |
|
| 82 |
-
|
| 83 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MandMP/math_model`](https://huggingface.co/cs-552-2026-MandMP/math_model)
|
| 4 |
- **Owner(s):** group **MandMP**
|
| 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 | 0.2000 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `28`
|
| 28 |
- **overall** (8/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `28`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
+
Okay, so Pat is choosing six cookies from a tray that has chocolate chip, oatmeal, and peanut butter cookies. There's at least six of each kind available. And since cookies of the same kind are indistinct, I need to figure out how many different ways she can choose them.
|
| 34 |
|
| 35 |
+
First, let me make sure I understand the problem correctly. It says there are at least six of each type available. So, for exa
|
| 36 |
|
| 37 |
+
... [truncated 823 chars] ...
|
| 38 |
|
| 39 |
+
e previous result.
|
| 40 |
|
| 41 |
+
Therefore, the answer is 28.
|
| 42 |
|
| 43 |
+
But just to make sure, let me think of another way. Let me consider that since there are at least six of each kind available, but Pat is only selecting six cookies. So, the number of chocolate chip cookies she can take is between 0 and 6, same with the others. But since the total is 6, the maximum number of any one kind is 6. So, the problem is equivalent to the number of non-negative integer solutions to c + o + p = 6. Which is C(6 + 3 -1, 3 -1) = C(8,2) = 28.
|
| 44 |
|
| 45 |
+
Therefore, I think the answer is 28.
|
| 46 |
|
| 47 |
+
But maybe I made a mistake in assuming that the upper bounds are redundant? Let me think again. Suppose that there were, for example, only five cookies of each kind available. Then, Pat couldn't take more than five of any kind. But since she is only taking six, that would be impossible. However, in our problem, since there are at least six cookies of each kind available, Pat can take up to six of any kind, which is exactly the number she is taking. Therefore, the upper bounds are not restrictive. Therefore, the answer is indeed 28.
|
| 48 |
+
|
| 49 |
+
Therefore, I think the answer is 28, so \boxed{28}.
|
| 50 |
|
| 51 |
**Final Answer**
|
| 52 |
+
\boxed{28}
|
| 53 |
</think>
|
| 54 |
|
| 55 |
+
\boxed{28}
|
| 56 |
```
|
| 57 |
|
| 58 |
**Incorrect** (1 shown)
|
| 59 |
|
| 60 |
+
- **reference**: `31`
|
| 61 |
- **overall** (0/8 completions correct)
|
| 62 |
- **extracted** (✗): `<no answer>`
|
| 63 |
- **completion**:
|
| 64 |
|
| 65 |
```text
|
| 66 |
+
Okay, so I need to solve this problem where we have integers a, b, c with c ≤ 2025, and the equation |x² + a x + b| = c has exactly 3 distinct integer solutions for x. Then I have to find how many possible values of c there are.
|
|
|
|
|
|
|
| 67 |
|
| 68 |
+
First, let me parse the equation. The absolute value of a quadratic expression equals c. So, |x² + a x + b| = c implies that either x² + a x + b = c or x² + a x + b = -c.
|
| 69 |
|
| 70 |
+
... [truncated 822 chars] ...
|
|
|
|
|
|
|
| 71 |
|
| 72 |
+
(discriminant zero) and Q2 has two roots. Wait, but earlier we thought that Case 2 was impossible because m = c and m < -c. But if we consider that, then m = c and m < -c ⇒ c < -c ⇒ c < 0. But c is non-negative, so this is impossible. Therefore, Case 2 is invalid. Therefore, only Case 1 is possible: Q1 has two roots, Q2 has one root. Therefore, only the c's from the case where Q2 discriminant is zero and Q1 discriminant is positive.
|
| 73 |
|
| 74 |
+
But wait, there's another possibility. Suppose that Q2 has two roots, but Q1 has one root. Wait, but that would mean that the equation |quadratic| = c has two roots from Q2 and one root from Q1, totaling three. However, in that case, Q1 would have one root (discriminant zero) and Q2 would have two roots (discriminant positive). Therefore, similar to before, but with different signs. Let me check.
|
| 75 |
|
| 76 |
+
If Q1 has one root (discriminant zero) and Q2 has two roots (discriminant positive). Then, similar logic applies. Let me try.
|
| 77 |
|
| 78 |
+
In this case, Q1: x² + a x + (b - c) = 0 has discriminant zero ⇒ a² = 4(b - c).
|
| 79 |
|
| 80 |
+
Q2: x² + a x + (b + c) = 0 has discriminant positive ⇒ a² - 4(b + c) > 0 ⇒ 4(b - c) - 4(b + c) = -8c > 0 ⇒ -8c > 0 ⇒ c < 0. But again, c is non-negative
|
| 81 |
```
|