Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use cs-552-2026-the-transformers/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-the-transformers/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-the-transformers/math_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-the-transformers/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-the-transformers/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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cs-552-2026-the-transformers/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-the-transformers/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-the-transformers/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-the-transformers/math_model
- SGLang
How to use cs-552-2026-the-transformers/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-the-transformers/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-the-transformers/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-the-transformers/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-the-transformers/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-the-transformers/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-the-transformers/math_model
Update Automated MNLP evaluation report (2026-06-11)
Browse files- EVAL_REPORT.md +92 -107
EVAL_REPORT.md
CHANGED
|
@@ -2,16 +2,16 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-the-transformers/math_model`](https://huggingface.co/cs-552-2026-the-transformers/math_model)
|
| 4 |
- **Owner(s):** group **the-transformers**
|
| 5 |
-
- **Generated at:** 2026-06-
|
| 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:** [`
|
| 13 |
- **Message:** Update model
|
| 14 |
-
- **Committed:** 2026-06-
|
| 15 |
|
| 16 |
## Summary
|
| 17 |
|
|
@@ -30,130 +30,115 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
-
- **reference**: `
|
| 34 |
-
- **overall** (
|
| 35 |
-
- **extracted** (✓): `
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
-
Okay,
|
| 41 |
-
|
| 42 |
-
First, in circular permutations, when arranging n people around a circ
|
| 43 |
|
| 44 |
... [truncated 823 chars] ...
|
| 45 |
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
(
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
$$
|
| 94 |
-
5! \times 3! = 120 \times 6 = 720
|
| 95 |
-
$$
|
| 96 |
-
|
| 97 |
-
---
|
| 98 |
-
|
| 99 |
-
### **Final Answer**
|
| 100 |
-
|
| 101 |
-
$$
|
| 102 |
-
\boxed{720}
|
| 103 |
-
$$
|
| 104 |
```
|
| 105 |
|
| 106 |
**Incorrect** (1 shown)
|
| 107 |
|
| 108 |
-
- **reference**: `$
|
| 109 |
- **overall** (0/8 completions correct)
|
| 110 |
-
- **extracted** (✗): `
|
| 111 |
- **completion**:
|
| 112 |
|
| 113 |
```text
|
| 114 |
<think>
|
| 115 |
-
Okay,
|
| 116 |
|
| 117 |
-
|
| 118 |
|
| 119 |
-
... [truncated
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
|
| 121 |
-
|
| 122 |
-
We need \( f(u+3) - f(u+0) \equiv 0 \pmod{4} \) and \( f(u+3+1) - f(u+1) \equiv 0 \pmod{4} \).
|
| 123 |
-
- For \( u = 1 \):
|
| 124 |
-
\[
|
| 125 |
-
f(1+3) - f(1) = f(4) - f(1) = 1 - 1 = 0 \pmod{4}
|
| 126 |
-
\]
|
| 127 |
-
\[
|
| 128 |
-
f(1+3+1) - f(1+1) = f(5) - f(2) = 5 - 1 = 4 \equiv 0 \pmod{4}
|
| 129 |
-
\]
|
| 130 |
-
Both conditions are satisfied.
|
| 131 |
-
- Therefore, \( v = 3 \) is valid.
|
| 132 |
-
|
| 133 |
-
- **Case \( v = 4 \):**
|
| 134 |
-
We need \( f(u+4) - f(u) \equiv 0 \pmod{4} \), \( f(u+4+1) - f(u+1) \equiv 0 \pmod{4} \), and \( f(u+4+2) - f(u+2) \equiv 0 \pmod{4} \).
|
| 135 |
-
- For \( u = 3 \):
|
| 136 |
-
\[
|
| 137 |
-
f(3+4) - f(3) = f(7) - f(3) = 7 - 3 = 4 \equiv 0 \pmod{4}
|
| 138 |
-
\]
|
| 139 |
-
\[
|
| 140 |
-
f(3+4+1) - f(3+1) = f(8) - f(4) = 1 - 1 = 0 \pmod{4}
|
| 141 |
-
\]
|
| 142 |
-
\[
|
| 143 |
-
f(3+4+2) - f(3+2) = f(9) - f(5) = 9 - 5 = 4 \equiv 0 \pmod{4}
|
| 144 |
-
\]
|
| 145 |
-
All conditions are satisfied.
|
| 146 |
-
- However, for \( k = 3 \):
|
| 147 |
-
\[
|
| 148 |
-
f(3+4+3) - f(3+3) = f(10) - f(6) = 5 - 3 = 2 \not\equiv 0 \pmod{4}
|
| 149 |
-
\]
|
| 150 |
-
This fails.
|
| 151 |
-
- Therefore, \( v = 4 \) is not valid.
|
| 152 |
-
|
| 153 |
-
4. **Conclusion:**
|
| 154 |
-
After checking all cases, the only valid values of \( v \) are \( 1 \) and \( 3 \).
|
| 155 |
|
|
|
|
| 156 |
\[
|
| 157 |
-
|
| 158 |
\]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-the-transformers/math_model`](https://huggingface.co/cs-552-2026-the-transformers/math_model)
|
| 4 |
- **Owner(s):** group **the-transformers**
|
| 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:** [`f9658b7`](https://huggingface.co/cs-552-2026-the-transformers/math_model/commit/f9658b7782b5e50dd8aa2a81f67c1d03d3476f92)
|
| 13 |
- **Message:** Update model
|
| 14 |
+
- **Committed:** 2026-06-10T17:25:31+00:00
|
| 15 |
|
| 16 |
## Summary
|
| 17 |
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `40_9`
|
| 34 |
+
- **overall** (7/8 completions correct)
|
| 35 |
+
- **extracted** (✓): `40_9`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
+
Okay, let's see. I need to subtract two numbers in base 9: 58₉ minus 18₉. Hmm, base 9... I remember that subtracting in different bases can be similar to decimal, but you have to remember that each digit goes from 0 to 8 instead of 0 to 9. So maybe I should convert both numbers to base 10, subtract them, and then convert the result back to base 9? That might be easier for me, since I'm mor
|
|
|
|
|
|
|
| 41 |
|
| 42 |
... [truncated 823 chars] ...
|
| 43 |
|
| 44 |
+
I think the answer is correct.
|
| 45 |
+
</think>
|
| 46 |
+
|
| 47 |
+
To solve the problem of evaluating \(58_9 - 18_9\) and writing the result in base 9, we can follow these steps:
|
| 48 |
+
|
| 49 |
+
1. **Convert both numbers to base 10:**
|
| 50 |
+
- Convert \(58_9\) to base 10:
|
| 51 |
+
\[
|
| 52 |
+
58_9 = 5 \times 9^1 + 8 \times 9^0 = 5 \times 9 + 8 = 45 + 8 = 53_{10}
|
| 53 |
+
\]
|
| 54 |
+
- Convert \(18_9\) to base 10:
|
| 55 |
+
\[
|
| 56 |
+
18_9 = 1 \times 9^1 + 8 \times 9^0 = 1 \times 9 + 8 = 9 + 8 = 17_{10}
|
| 57 |
+
\]
|
| 58 |
+
|
| 59 |
+
2. **Subtract the two base 10 numbers:**
|
| 60 |
+
\[
|
| 61 |
+
53_{10} - 17_{10} = 36_{10}
|
| 62 |
+
\]
|
| 63 |
+
|
| 64 |
+
3. **Convert the result back to base 9:**
|
| 65 |
+
- Divide 36 by 9 to find the quotient and remainder:
|
| 66 |
+
\[
|
| 67 |
+
36 \div 9 = 4 \text{ remainder } 0
|
| 68 |
+
\]
|
| 69 |
+
- Therefore, \(36_{10}\) in base 9 is \(40_9\).
|
| 70 |
+
|
| 71 |
+
4. **Verify the result:**
|
| 72 |
+
- Convert \(40_9\) back to base 10:
|
| 73 |
+
\[
|
| 74 |
+
40_9 = 4 \times 9^1 + 0 \times 9^0 = 4 \times 9 + 0 = 36_{10}
|
| 75 |
+
\]
|
| 76 |
+
- Convert \(58_9\) and \(18_9\) back to base 10:
|
| 77 |
+
\[
|
| 78 |
+
58_9 = 53_{10}, \quad 18_9 = 17_{10}
|
| 79 |
+
\]
|
| 80 |
+
- Subtract the base 10 numbers:
|
| 81 |
+
\[
|
| 82 |
+
53_{10} - 17_{10} = 36_{10}
|
| 83 |
+
\]
|
| 84 |
+
- Convert \(36_{10}\) back to base 9:
|
| 85 |
+
\[
|
| 86 |
+
36_{10} = 40_9
|
| 87 |
+
\]
|
| 88 |
+
|
| 89 |
+
Thus, the final answer is \(\boxed{40_9}\).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
```
|
| 91 |
|
| 92 |
**Incorrect** (1 shown)
|
| 93 |
|
| 94 |
+
- **reference**: `$f(x,y)= g(x+y, xy(x-y)^{2})$ for some polynomial $g$`
|
| 95 |
- **overall** (0/8 completions correct)
|
| 96 |
+
- **extracted** (✗): `c`
|
| 97 |
- **completion**:
|
| 98 |
|
| 99 |
```text
|
| 100 |
<think>
|
| 101 |
+
Okay, let's try to figure out this problem. So, we need to find all polynomials f(x, y) in complex numbers such that for any complex numbers a and b, the equation f(a², b²) equals f((a - b)² / 2, (a + b)² / 2). Hmm, interesting. Let me start by understanding what this condition means.
|
| 102 |
|
| 103 |
+
First, maybe I should consider specific values for a and b to see if I can spot a pattern or figure out t
|
| 104 |
|
| 105 |
+
... [truncated 822 chars] ...
|
| 106 |
+
|
| 107 |
+
+ q}{2}\right)a^2 + \left(\frac{p + q}{2}\right)b^2 - pqab + r.
|
| 108 |
+
\]
|
| 109 |
+
Equating the coefficients with the left-hand side:
|
| 110 |
+
\[
|
| 111 |
+
p a^2 + q b^2 + r = \left(\frac{p + q}{2}\right)a^2 + \left(\frac{p + q}{2}\right)b^2 - pqab + r.
|
| 112 |
+
\]
|
| 113 |
+
For this to hold for all $ a $ and $ b $, the coefficients must match:
|
| 114 |
+
\[
|
| 115 |
+
p = \frac{p + q}{2} \implies 2p = p + q \implies q = p,
|
| 116 |
+
\]
|
| 117 |
+
\[
|
| 118 |
+
q = \frac{p + q}{2} \implies 2q = p + q \implies p = q,
|
| 119 |
+
\]
|
| 120 |
+
\[
|
| 121 |
+
-pq = 0 \implies pq = 0 \implies p = 0 \text{ (since } p \neq 0).
|
| 122 |
+
\]
|
| 123 |
+
Thus, the only solution for linear polynomials is $ f(x, y) = 0 $, which is a constant.
|
| 124 |
|
| 125 |
+
#### Quadratic Polynomials
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
|
| 127 |
+
Assume $ f(x, y) = Ax^2 + By^2 + Cxy + Dx + Ey + F $. Substitute into the equation and equate coefficients. This leads to:
|
| 128 |
\[
|
| 129 |
+
A = B = C = D = E = F = 0.
|
| 130 |
\]
|
| 131 |
+
Thus, the only solution is $ f(x, y) = c $.
|
| 132 |
+
|
| 133 |
+
### Step 4: Higher-Degree Polynomials
|
| 134 |
+
|
| 135 |
+
Higher-degree polynomials will similarly force all coefficients to zero, confirming that only constant polynomials satisfy the condition.
|
| 136 |
+
|
| 137 |
+
### Conclusion
|
| 138 |
+
|
| 139 |
+
After testing various forms and deriving constraints, the only polynomials $ f(x, y) \in \mathbb{C}[x, y] \) that satisfy the given functional equation are the constant polynomials.
|
| 140 |
+
|
| 141 |
+
$$
|
| 142 |
+
\boxed{c}
|
| 143 |
+
$$
|
| 144 |
```
|