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 (2026-05-29)
#12
by zechen-nlp - opened
- EVAL_REPORT.md +79 -23
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 |
|
|
@@ -24,35 +24,59 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
-
- **overall** (
|
| 29 |
-
- **extracted** (✓): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
-
Okay, so
|
| 34 |
|
| 35 |
-
|
|
|
|
|
|
|
| 36 |
|
| 37 |
... [truncated 823 chars] ...
|
| 38 |
|
| 39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
-
|
| 42 |
|
| 43 |
-
But
|
| 44 |
|
| 45 |
-
|
| 46 |
|
| 47 |
-
|
| 48 |
|
| 49 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
**Final Answer**
|
| 52 |
-
\boxed{
|
| 53 |
</think>
|
| 54 |
|
| 55 |
-
\boxed{
|
| 56 |
```
|
| 57 |
|
| 58 |
**Incorrect** (1 shown)
|
|
@@ -63,19 +87,51 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 63 |
- **completion**:
|
| 64 |
|
| 65 |
```text
|
| 66 |
-
Okay, so I need to solve this problem where we have
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
-
|
| 69 |
|
| 70 |
-
|
| 71 |
|
| 72 |
-
|
| 73 |
|
| 74 |
-
|
| 75 |
|
| 76 |
-
|
| 77 |
|
| 78 |
-
|
| 79 |
|
| 80 |
-
|
| 81 |
```
|
|
|
|
| 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:** 2026-05-29T06:54:15+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 | 0.1900 | ok |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `3`
|
| 28 |
+
- **overall** (7/8 completions correct)
|
| 29 |
+
- **extracted** (✓): `3`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
+
Okay, so I need to solve this problem about treeks, squigs, and goolees. Let me read it again:
|
| 34 |
|
| 35 |
+
"Suppose 10 treeks have the same weight as 3 squigs plus 1 goolee, and 2 treeks together with 1 goolee weigh as much as 1 squig. Determine how many treeks have a combined weight equal to that of 1 squig."
|
| 36 |
+
|
| 37 |
+
Alright, so there are three different units: treeks, squigs, and goolees. The problem gives me two
|
| 38 |
|
| 39 |
... [truncated 823 chars] ...
|
| 40 |
|
| 41 |
+
herefore, x = 3T / T = 3. So, 3 treeks equal 1 squig.
|
| 42 |
+
|
| 43 |
+
Wait, so the answer is 3?
|
| 44 |
+
|
| 45 |
+
Let me check again.
|
| 46 |
+
|
| 47 |
+
From equation (1): 10T = 3S + G
|
| 48 |
+
|
| 49 |
+
From equation (2): 2T + G = S
|
| 50 |
+
|
| 51 |
+
We can substitute S from equation (2) into equation (1):
|
| 52 |
+
|
| 53 |
+
10T = 3*(2T + G) + G => 10T = 6T + 3G + G => 10T = 6T + 4G => 4T = 4G => T = G.
|
| 54 |
+
|
| 55 |
+
Then S = 2T + G = 2T + T = 3T. Therefore, 1 squig is 3 treeks. So yes, 3 treeks equal 1 squig.
|
| 56 |
|
| 57 |
+
So the answer is 3. Therefore, boxed answer is \boxed{3}.
|
| 58 |
|
| 59 |
+
But let me think again if I did everything correctly. Maybe I made an assumption?
|
| 60 |
|
| 61 |
+
Wait, the problem says "how many treeks have a combined weight equal to that of 1 squig". So, if 1 squig is 3 treeks, then 3 treeks = 1 squig. So yes, answer is 3.
|
| 62 |
|
| 63 |
+
Alternatively, maybe I should check with actual numbers. Let me assign some numbers.
|
| 64 |
|
| 65 |
+
Let me assume that T = G = 1 unit. Then S = 3T = 3 units.
|
| 66 |
+
|
| 67 |
+
Check equation (1): 10T = 10*1 = 10. On the other side, 3S + G = 3*3 + 1 = 9 + 1 = 10. Correct.
|
| 68 |
+
|
| 69 |
+
Equation (2): 2T + G = 2*1 + 1 = 3, which equals S = 3. Correct.
|
| 70 |
+
|
| 71 |
+
So yes, that works. Therefore, 3 treeks equal 1 squig. So answer is 3.
|
| 72 |
+
|
| 73 |
+
Therefore, I think the answer is 3. So \boxed{3} is the answer.
|
| 74 |
|
| 75 |
**Final Answer**
|
| 76 |
+
\boxed{3}
|
| 77 |
</think>
|
| 78 |
|
| 79 |
+
\boxed{3}
|
| 80 |
```
|
| 81 |
|
| 82 |
**Incorrect** (1 shown)
|
|
|
|
| 87 |
- **completion**:
|
| 88 |
|
| 89 |
```text
|
| 90 |
+
Okay, so I need to solve this problem where we have an equation |x² + a x + b| = c, and there are three distinct integer solutions for x. The variables a, b, and c are integers, and c is less than or equal to 2025. We need to find how many possible values of c there are.
|
| 91 |
+
|
| 92 |
+
First, let me recall that absolute value equations like |f(x)| = c can be split into two cases: f(x) = c and f(x) = -c. So, in
|
| 93 |
+
|
| 94 |
+
... [truncated 823 chars] ...
|
| 95 |
+
|
| 96 |
+
uting c = b - r1 r2 into a² = 4(b + c):
|
| 97 |
+
|
| 98 |
+
a² = 4(b + b - r1 r2) = 4(2b - r1 r2)
|
| 99 |
+
|
| 100 |
+
But also, from Q1, a = -(r1 + r2). Therefore, a² = (r1 + r2)^2.
|
| 101 |
+
|
| 102 |
+
Therefore:
|
| 103 |
+
|
| 104 |
+
(r1 + r2)^2 = 8b - 4 r1 r2
|
| 105 |
+
|
| 106 |
+
Let me write that equation:
|
| 107 |
+
|
| 108 |
+
(r1 + r2)^2 = 8b - 4 r1 r2
|
| 109 |
+
|
| 110 |
+
Expanding left side:
|
| 111 |
+
|
| 112 |
+
r1² + 2 r1 r2 + r2² = 8b - 4 r1 r2
|
| 113 |
+
|
| 114 |
+
Bring all terms to left side:
|
| 115 |
+
|
| 116 |
+
r1² + 2 r1 r2 + r2² + 4 r1 r2 - 8b = 0 ⇒ r1² + 6 r1 r2 + r2² - 8b = 0
|
| 117 |
+
|
| 118 |
+
Therefore:
|
| 119 |
+
|
| 120 |
+
8b = r1² + 6 r1 r2 + r2²
|
| 121 |
+
|
| 122 |
+
Therefore:
|
| 123 |
|
| 124 |
+
b = [r1² + 6 r1 r2 + r2²]/8
|
| 125 |
|
| 126 |
+
But since b must be integer, the numerator must be divisible by 8.
|
| 127 |
|
| 128 |
+
Similarly, since c = b - r1 r2, then c = [r1² + 6 r1 r2 + r2²]/8 - r1 r2 = [r1² + 6 r1 r2 + r2² - 8 r1 r2]/8 = [r1² - 2 r1 r2 + r2²]/8 = (r1 - r2)^2 / 8
|
| 129 |
|
| 130 |
+
Therefore, c = (r1 - r2)^2 / 8
|
| 131 |
|
| 132 |
+
Since c must be integer, (r1 - r2)^2 must be divisible by 8. Therefore, (r1 - r2)^2 ≡ 0 mod 8 ⇒ r1 - r2 is divisible by 2√2? Wait, no. Wait, if (r1 - r2)^2 is divisible by 8, then (r1 - r2)^2 must be divisible by 8. Let me think.
|
| 133 |
|
| 134 |
+
If (r1 - r2)^2 is divisible by 8, then (r1 - r2)^2 has factors of 2^3. Therefore, (r1 - r2)^2 must be divisible by 8 ⇒ (r1 - r2)^2 is divisible by 8 ⇒ (r1 - r2) is divisible by 2√2? Wait, no. Let me think again.
|
| 135 |
|
| 136 |
+
Suppose that (r1 - r2
|
| 137 |
```
|