Instructions to use cs-552-2026-barn/multilingual_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-barn/multilingual_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-barn/multilingual_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-barn/multilingual_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-barn/multilingual_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-barn/multilingual_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-barn/multilingual_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-barn/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-barn/multilingual_model
- SGLang
How to use cs-552-2026-barn/multilingual_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-barn/multilingual_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-barn/multilingual_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-barn/multilingual_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-barn/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-barn/multilingual_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-barn/multilingual_model
Automated MNLP evaluation report (2026-06-04)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +87 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-barn/multilingual_model`](https://huggingface.co/cs-552-2026-barn/multilingual_model)
|
| 4 |
+
- **Owner(s):** group **barn**
|
| 5 |
+
- **Generated at:** 2026-06-04T19:45:28+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 |
+
## Summary
|
| 11 |
+
|
| 12 |
+
| Benchmark | Accuracy | Status |
|
| 13 |
+
|---|---:|---|
|
| 14 |
+
| Math | — | not run |
|
| 15 |
+
| Knowledge | — | not run |
|
| 16 |
+
| Multilingual | 0.2300 | ok |
|
| 17 |
+
| Safety | — | not run |
|
| 18 |
+
|
| 19 |
+
## Sample completions
|
| 20 |
+
|
| 21 |
+
_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
|
| 22 |
+
|
| 23 |
+
### Multilingual
|
| 24 |
+
|
| 25 |
+
**Correct** (1 shown)
|
| 26 |
+
|
| 27 |
+
- **reference**: `A`
|
| 28 |
+
- **overall** (1/1 completions correct)
|
| 29 |
+
- **extracted** (✓): `A`
|
| 30 |
+
- **completion**:
|
| 31 |
+
|
| 32 |
+
```text
|
| 33 |
+
<think>
|
| 34 |
+
|
| 35 |
+
</think>
|
| 36 |
+
|
| 37 |
+
A. Квалиметрической шкалой
|
| 38 |
+
|
| 39 |
+
**Обоснование:**
|
| 40 |
+
Тройка формальных объектов — это концепция, которая используется в квалиметрии (науке о количественных характеристиках). Она описывает три основные ступени или уровни, на которых можно оценивать объекты, обычно в рамках шкалирования. Эти ступени обычно включают:
|
| 41 |
+
1. **Нулевая** (или **нулевая**),
|
| 42 |
+
2. **Положительная**,
|
| 43 |
+
3. **Негативная**.
|
| 44 |
+
|
| 45 |
+
Эта тройка формальных объектов называется **квалиметрической шкалой**.
|
| 46 |
+
|
| 47 |
+
Таким образом, правильный ответ:
|
| 48 |
+
$\boxed{A}$
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
**Incorrect** (1 shown)
|
| 52 |
+
|
| 53 |
+
- **reference**: `A`
|
| 54 |
+
- **overall** (0/1 completions correct)
|
| 55 |
+
- **extracted** (✗): `C`
|
| 56 |
+
- **completion**:
|
| 57 |
+
|
| 58 |
+
```text
|
| 59 |
+
<think>
|
| 60 |
+
|
| 61 |
+
</think>
|
| 62 |
+
|
| 63 |
+
The most likely cause of the patient's condition is **C. जन्मजात महाधमनी स्टेनोसिस (Congenital Patent Ductus Arteriosus, PDA)**.
|
| 64 |
+
|
| 65 |
+
### Explanation:
|
| 66 |
+
|
| 67 |
+
- The patient is **32 weeks pregnant** and has **preeclampsia** (high blood pressure and proteinuria), which is a **high-risk pregnancy**.
|
| 68 |
+
- She has **tachycardia (132 bpm)**, **tachypnea (32 bpm)**, and **tachypnea (32 bpm)**, which
|
| 69 |
+
|
| 70 |
+
... [truncated 453 chars] ...
|
| 71 |
+
|
| 72 |
+
vated**, and **tachycardia** is a common finding in **preeclampsia** and **cardiomegaly**.
|
| 73 |
+
- The **pulsation** and **oxygen saturation** are **normal**, but the **tachycardia and tachypnea** are consistent with **cardiomegaly** and **preeclampsia**.
|
| 74 |
+
- The **heart sounds** and **heart rate** suggest **increased cardiac workload**, which is commonly seen in **preeclampsia** and **congenital heart disease**.
|
| 75 |
+
|
| 76 |
+
### Key clues:
|
| 77 |
+
- The **tachycardia** and **tachypnea** are **not** due to **respiratory distress** (e.g., asthma, COPD), but rather due to **cardiac disease** and **preeclampsia**.
|
| 78 |
+
- The **tachycardia** is **not** due to **anemia** or **hypothyroidism** (the patient is **not** hypothyroid, and **thyroxine** is being used).
|
| 79 |
+
- The **heart rate** is **not** due to **tachypnea** or **respiratory distress**, but due to **cardiac workload** and **preeclampsia**.
|
| 80 |
+
|
| 81 |
+
### Conclusion:
|
| 82 |
+
The most likely **cause of the patient's condition** is **C. जन्मजात महाधमनी स्टेनोसिस (Congenital Patent Ductus Arteriosus)**, which is a **congenital heart defect** that can lead to **increased cardiac workload**, **tachycardia**, and **tachypnea** in **pregnant women** with **preeclampsia**.
|
| 83 |
+
|
| 84 |
+
$$
|
| 85 |
+
\boxed{C}
|
| 86 |
+
$$
|
| 87 |
+
```
|