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 (2026-05-23)
#6
by zechen-nlp - opened
- EVAL_REPORT.md +23 -33
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** β 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** β yo
|
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
-
| Math | 0.
|
| 15 |
| Knowledge | β | not run |
|
| 16 |
| Multilingual | β | not run |
|
| 17 |
| Safety | β | not run |
|
|
@@ -24,64 +24,54 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
-
- **overall** (
|
| 29 |
-
- **extracted** (β): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
-
Okay, so I need to
|
| 34 |
|
| 35 |
-
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
-
|
| 40 |
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
So, I think my answer is correct.
|
| 44 |
-
|
| 45 |
-
But just to make sure, let me plug x = 4 back into the original equation.
|
| 46 |
-
|
| 47 |
-
Left side: 10^4 - 10.
|
| 48 |
-
|
| 49 |
-
10^4 is 10,000. 10,000 - 10 is 9,990. Which matches the right side of the equation.
|
| 50 |
|
| 51 |
-
|
| 52 |
|
| 53 |
-
I
|
| 54 |
|
| 55 |
-
|
| 56 |
|
| 57 |
-
|
| 58 |
|
| 59 |
-
|
| 60 |
|
| 61 |
-
I think
|
| 62 |
|
| 63 |
**Final Answer**
|
| 64 |
-
|
| 65 |
</think>
|
| 66 |
|
| 67 |
-
\boxed{
|
| 68 |
```
|
| 69 |
|
| 70 |
**Incorrect** (1 shown)
|
| 71 |
|
| 72 |
-
- **reference**: `
|
| 73 |
- **overall** (0/8 completions correct)
|
| 74 |
- **extracted** (β): `<no answer>`
|
| 75 |
- **completion**:
|
| 76 |
|
| 77 |
```text
|
| 78 |
-
Okay, so I need to
|
| 79 |
-
|
| 80 |
-
... [truncated 823 chars] ...
|
| 81 |
|
| 82 |
-
|
| 83 |
|
| 84 |
-
|
| 85 |
|
| 86 |
-
|
| 87 |
```
|
|
|
|
| 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:** 2026-05-23T14:37:35+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** β you do not need to merge it. The next nightly run will refresh this file._
|
|
|
|
| 11 |
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
+
| Math | 0.1700 | ok |
|
| 15 |
| Knowledge | β | not run |
|
| 16 |
| Multilingual | β | not run |
|
| 17 |
| Safety | β | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `23`
|
| 28 |
+
- **overall** (5/8 completions correct)
|
| 29 |
+
- **extracted** (β): `23`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
+
Okay, so I need to figure out how to express the expression β2 + 1/β2 + β3 + 1/β3 as a fraction with some radicals in the numerator and a rational denominator, and then find the sum of a, b, and c where c is minimized. Alright, let me start by trying to simplify each term first.
|
| 34 |
|
| 35 |
+
First, let me write down the expression again to make sure I have it right:
|
| 36 |
|
| 37 |
+
β2 + 1/β2 + β3 + 1/β3.
|
| 38 |
|
| 39 |
+
Hmm, okay. So each
|
| 40 |
|
| 41 |
+
... [truncated 823 chars] ...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
+
e. So, that gives (3/2)β2 + (4/3)β3. Which is same as before. So, same result.
|
| 44 |
|
| 45 |
+
Alternatively, maybe I can write the entire expression as a single fraction by multiplying numerator and denominator by something? Wait, but that's not helpful. For example, suppose I multiply numerator and denominator by β2*β3? Let me try that.
|
| 46 |
|
| 47 |
+
Let me think. Suppose I have (3/2)β2 + (4/3)β3. Let me write this as [ (3/2)β2 + (4/3)β3 ] * [ (2β3 + 3β2) / (2β3 + 3β2) ) ]? Wait, that seems arbitrary. Maybe not helpful.
|
| 48 |
|
| 49 |
+
Alternatively, maybe think of the expression as Aβ2 + Bβ3 where A and B are numbers, and then find A and B such that Aβ2 + Bβ3 is equal to the original expression. But that's essentially what I did earlier.
|
| 50 |
|
| 51 |
+
Alternatively, maybe there's a way to combine the terms with different radicals? For example, if I can write them as something over 6, but that's already done. So I think my answer is correct.
|
| 52 |
|
| 53 |
+
Therefore, I think the answer is 23. Wait, but let me check once more. Let me check if 9, 8, 6 are positive integers. Yes. And c is minimized. Since 6 is the LCD of 2 and 3, so yes. Therefore, the answer is 23. Therefore, I think the answer is 23.
|
| 54 |
|
| 55 |
**Final Answer**
|
| 56 |
+
\boxed{23}
|
| 57 |
</think>
|
| 58 |
|
| 59 |
+
\boxed{23}
|
| 60 |
```
|
| 61 |
|
| 62 |
**Incorrect** (1 shown)
|
| 63 |
|
| 64 |
+
- **reference**: `82`
|
| 65 |
- **overall** (0/8 completions correct)
|
| 66 |
- **extracted** (β): `<no answer>`
|
| 67 |
- **completion**:
|
| 68 |
|
| 69 |
```text
|
| 70 |
+
Okay, so I need to figure out how many colorings of the 2x2 grid satisfy the condition that each square has exactly two red sides and two blue sides. Let me try to visualize the grid. It's a 2x2 grid, so there are four squares. Each square has four sides, but adjacent squares share sides. The problem says that each square must have exactly two red sides and two blue sides.
|
|
|
|
|
|
|
| 71 |
|
| 72 |
+
First, let me think ab
|
| 73 |
|
| 74 |
+
... [truncated 823 chars] ...
|
| 75 |
|
| 76 |
+
then square D's right side is adjacent to square C? No, square D is to the right of square C, so square D's right side is adjacent to square C? No, square D is adjacent to square C on the left. The right side of square D is adjacent to square C? No, square D is adjacent to square C on the left. The right side of square D is the same as the left side of square C? Wait, no. If you have square C and square D next to each other, then square D's left side is adjacent to square C, and square C's right side is adjacent to square D. Therefore, the left side of square D is adjacent to square C, and the right side of square D is adjacent to square C? No, square D's right side is adjacent to square C? No, square D is adjacent to square C on the left. The right side of square D is adjacent to square D's right side, which is not adjacent to any square. Wait, square D is on the bottom-right corner. Its left side is adjacent to square C, its right side is adjacent to square D's right edge, which is not adjacent to any square. Similarly, its top side is adjacent to square D's top edge, which is not adjacent to any square. Its bottom side is adjacent to square D's bottom edge, which is not adjacent
|
| 77 |
```
|