Instructions to use cs-552-2026-camykaz/math_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-camykaz/math_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-camykaz/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-camykaz/math_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-camykaz/math_model") 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-camykaz/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-camykaz/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-camykaz/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-camykaz/math_model
- SGLang
How to use cs-552-2026-camykaz/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-camykaz/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-camykaz/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-camykaz/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-camykaz/math_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-camykaz/math_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-camykaz/math_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +122 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-camykaz/math_model`](https://huggingface.co/cs-552-2026-camykaz/math_model)
|
| 4 |
+
- **Owner(s):** group **camykaz**
|
| 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:** [`cc7a572`](https://huggingface.co/cs-552-2026-camykaz/math_model/commit/cc7a572d698cb4899527567350c6317c5a0751b7)
|
| 13 |
+
- **Message:** Upload v7 checkpoint 2400 math model
|
| 14 |
+
- **Committed:** 2026-06-06T21:39:38+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 |
+
Okay, so I need to figure out how many Trinkets are equivalent to 56 Drinkets. Let me start by understanding the problem step by step.
|
| 40 |
+
|
| 41 |
+
First, the exchange rates are given: 1 Trinket is worth 4 Blinkets, and 3 Blinkets are worth 7 Drinkets. So, I need to convert Drinkets to Blinkets first, and then Blinkets to Trinkets. That seems like a two-step conversion. Let me write down the exchange rates a
|
| 42 |
+
|
| 43 |
+
... [truncated 823 chars] ...
|
| 44 |
+
|
| 45 |
+
e just check once again.
|
| 46 |
+
|
| 47 |
+
If 6 Trinkets are equal to 6*4=24 Blinkets. And 24 Blinkets are equal to 24*(7/3) Drinkets, which is 24*(7/3)=56 Drinkets. Yes, that's exactly 56 Drinkets. So, that checks out. Therefore, the answer is 6 Trinkets.
|
| 48 |
+
|
| 49 |
+
**Final Answer**
|
| 50 |
+
The number of Trinkets in 56 Drinkets is \boxed{6}.
|
| 51 |
+
</think>
|
| 52 |
+
|
| 53 |
+
To express 56 Drinkets in Trinkets, we need to convert Drinkets to Blinkets and then Blinkets to Trinkets.
|
| 54 |
+
|
| 55 |
+
First, convert Drinkets to Blinkets using the exchange rate \(3 \text{ Blinkets} = 7 \text{ Drinkets}\). To find the number of Blinkets in 1 Drinket, we use the rate:
|
| 56 |
+
\[
|
| 57 |
+
1 \text{ Drinket} = \frac{3 \text{ Blinkets}}{7 \text{ Drinkets}} = \frac{3}{7} \text{ Blinkets}
|
| 58 |
+
\]
|
| 59 |
+
Next, convert 56 Drinkets to Blinkets:
|
| 60 |
+
\[
|
| 61 |
+
56 \text{ Drinkets} \times \frac{3}{7} \text{ Blinkets/Drinket} = \frac{56 \times 3}{7} \text{ Blinkets} = \frac{168}{7} \text{ Blinkets} = 24 \text{ Blinkets}
|
| 62 |
+
\]
|
| 63 |
+
|
| 64 |
+
Now, convert Blinkets to Trinkets using the exchange rate \(1 \text{ Trinket} = 4 \text{ Blinkets}\):
|
| 65 |
+
\[
|
| 66 |
+
24 \text{ Blinkets} \times \frac{1 \text{ Trinket}}{4 \text{ Blinkets}} = \frac{24}{4} \text{ Trinkets} = 6 \text{ Trinkets}
|
| 67 |
+
\]
|
| 68 |
+
|
| 69 |
+
Thus, the number of Trinkets in 56 Drinkets is \(\boxed{6}\).
|
| 70 |
+
```
|
| 71 |
+
|
| 72 |
+
**Incorrect** (1 shown)
|
| 73 |
+
|
| 74 |
+
- **reference**: `60750, 854130, 854970`
|
| 75 |
+
- **overall** (0/8 completions correct)
|
| 76 |
+
- **extracted** (✗): `854130`
|
| 77 |
+
- **completion**:
|
| 78 |
+
|
| 79 |
+
```text
|
| 80 |
+
Okay, let's see. I need to solve this problem where there's a function h from natural numbers to natural numbers excluding 1, and it satisfies the equation h(n) + h(n+1) = h(n+2)h(n+3) - 840 for every natural number n. Then, I have to determine all possible values that the sum from i=1 to 2025 of h(i) can take. Hmm, interesting.
|
| 81 |
+
|
| 82 |
+
First, let me parse the problem again. The function h maps natural n
|
| 83 |
+
|
| 84 |
+
... [truncated 822 chars] ...
|
| 85 |
+
|
| 86 |
+
= 2025 \times 30 = 60750
|
| 87 |
+
\]
|
| 88 |
+
|
| 89 |
+
2. **Periodic Alternating Solutions:**
|
| 90 |
+
- Consider the sequences that alternate between 2 and 842. For example:
|
| 91 |
+
\[
|
| 92 |
+
h(1) = 2, \quad h(2) = 842, \quad h(3) = 2, \quad h(4) = 842, \quad \ldots
|
| 93 |
+
\]
|
| 94 |
+
- Check the recurrence relation:
|
| 95 |
+
\[
|
| 96 |
+
h(1) + h(2) = 2 + 842 = 844
|
| 97 |
+
\]
|
| 98 |
+
\[
|
| 99 |
+
h(3)h(4) = 2 \cdot 842 = 1684 \implies 844 = 1684 - 840 = 844
|
| 100 |
+
\]
|
| 101 |
+
- This is valid. The sum for this alternating sequence is:
|
| 102 |
+
\[
|
| 103 |
+
\sum_{i=1}^{2025} h(i) = 1013 \times 2 + 1012 \times 842 = 2026 + 852104 = 854130
|
| 104 |
+
\]
|
| 105 |
+
- Similarly, if the sequence starts with 842:
|
| 106 |
+
\[
|
| 107 |
+
h(1) = 842, \quad h(2) = 2, \quad h(3) = 842, \quad h(4) = 2, \quad \ldots
|
| 108 |
+
\]
|
| 109 |
+
The sum is the same:
|
| 110 |
+
\[
|
| 111 |
+
\sum_{i=1}^{2025} h(i) = 1013 \times 842 + 1012 \times 2 = 854130
|
| 112 |
+
\]
|
| 113 |
+
|
| 114 |
+
3. **Other Potential Solutions:**
|
| 115 |
+
- Other potential solutions, such as starting with 30 and 2 or 842 and 2, were found to be invalid due to the recurrence relation constraints.
|
| 116 |
+
|
| 117 |
+
### Conclusion:
|
| 118 |
+
The only possible values for the sum \( \sum_{i=1}^{2025} h(i) \) are:
|
| 119 |
+
\[
|
| 120 |
+
\boxed{60750} \quad \text{and} \quad \boxed{854130}
|
| 121 |
+
\]
|
| 122 |
+
```
|