Instructions to use cs-552-2026-theattentionseekers/multilingual_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-theattentionseekers/multilingual_model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="cs-552-2026-theattentionseekers/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-theattentionseekers/multilingual_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-theattentionseekers/multilingual_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-theattentionseekers/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-theattentionseekers/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-theattentionseekers/multilingual_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-theattentionseekers/multilingual_model

SGLang

How to use cs-552-2026-theattentionseekers/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-theattentionseekers/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-theattentionseekers/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-theattentionseekers/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-theattentionseekers/multilingual_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-theattentionseekers/multilingual_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-theattentionseekers/multilingual_model
```

zechen-nlp commited on May 17

Commit

44c3742

verified ·

1 Parent(s): 0523912

Update Automated MNLP evaluation report (2026-05-17)

Browse files

Files changed (1) hide show

EVAL_REPORT.md +14 -35

EVAL_REPORT.md CHANGED Viewed

@@ -2,7 +2,7 @@
 - **Model repo:** [`cs-552-2026-theattentionseekers/multilingual_model`](https://huggingface.co/cs-552-2026-theattentionseekers/multilingual_model)
 - **Owner(s):** group **theattentionseekers**
-- **Generated at:** 2026-05-16T04:57:46+00:00 (UTC)
 - **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
 _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._
@@ -13,7 +13,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
 |---|---:|---|
 | Math | — | not run |
 | Knowledge | — | not run |
-| Multilingual | 0.4700 | ok |
 | Safety | — | not run |
 ## Sample completions
@@ -24,49 +24,28 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
 **Correct** (1 shown)
-- **reference**: `B`
 - **overall** (1/1 completions correct)
-- **extracted** (✓): `B`
 - **completion**:
     ```text
-    La opción correcta es:
-    **B. nominal.**
-    **Explicación:**
-    El valor nominal del dinero es el valor numérico que se asigna a una moneda o billete, sin considerar su valor de cambio o su poder de compra en el mercado. Este valor es establecido por instituciones financieras como el BCR (Banco Central de Reserva del Peru) en representación del Estado.
-    Las otras opciones:
-    - **A. de cambio:** Refiere al valor de cambio de una moneda en relación con otra, no al valor nominal.
-    - **C. real:** Refiere al valor de compra de una moneda en el mercado, no al valor establecido por instituciones.
-    - **D. extrínseco:** No es un término técnico en el contexto de los valores del dinero.
-    Por lo tanto, la respuesta correcta es:
-    $\boxed{B}$
     ```
 **Incorrect** (1 shown)
-- **reference**: `D`
 - **overall** (0/1 completions correct)
-- **extracted** (✗): `A`
 - **completion**:
     ```text
-    भूगोल शिक्षण को जुड़े संदर्भ में परिप्रेक्ष्य का विकास करना चाहिए जो निम्नलिखित मुद्दों से जुड़े हों:
-    - **संसाधन और संरक्षण** – भूगोल शिक्षण विकास और संरक्षण के बीच के अंतर को समझने में मदद करता है।
-    - **विकास और विस्थापन** – भूगोल शिक्षण विकास एवं विस्थापन के दौरान अनुभव और अवस्था के बीच के अंतर को समझने में मदद करता है।
-    - **विविधता में एकता से जुड़ी चुनौतियाँ** – भूगोल शिक्षण विविधता और एकता के बीच के अंतर को समझने में मदद करता है।
-    - **मानव विकास** – भूगोल शिक्षण मानव विकास के दौरान अनुभव और अवस्था के बीच के अंतर को समझने में मदद करता है।
-    सभी चार विकल्प भूगोल शिक्षण के विकास में जुड़े होते हैं। लेकिन यदि हम **संदर्भ में परिप्रेक्ष्य का विकास करने के लिए चुने जाने वाले अधिक अनुमान को देखे जाएँ तो**:
-    > **संसाधन और संरक्षण**, **विविधता में एकता से जुड़ी चुनौतियाँ**, और **मानव विकास** एक दिशा देने वाले मुद्दे होते हैं।
-    फिर उनमें **संसाधन और संरक्षण** और **मानव विकास** अधिक अनुमान देने वाले होते हैं।
-    ### अंतिम उत्तर:
-    \boxed{A}
     ```

 - **Model repo:** [`cs-552-2026-theattentionseekers/multilingual_model`](https://huggingface.co/cs-552-2026-theattentionseekers/multilingual_model)
 - **Owner(s):** group **theattentionseekers**
+- **Generated at:** 2026-05-17T04:52:19+00:00 (UTC)
 - **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
 _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._
 |---|---:|---|
 | Math | — | not run |
 | Knowledge | — | not run |
+| Multilingual | 0.0300 | ok |
 | Safety | — | not run |
 ## Sample completions
 **Correct** (1 shown)
+- **reference**: `C`
 - **overall** (1/1 completions correct)
+- **extracted** (✓): `C`
 - **completion**:
     ```text
+    <think>
+    Analyzing target text structures and parsing options. Eliminating contradictory options. Deducing logical verification values. Selecting option C as the optimal fit based on linguistic parameters.
+    </think>
+    \boxed{C}
     ```
 **Incorrect** (1 shown)
+- **reference**: `B`
 - **overall** (0/1 completions correct)
+- **extracted** (✗): `<no answer>`
 - **completion**:
     ```text
+    <think>
+    Analyzing target text structures and parsing options. Eliminating contradictory options. Deducing logical verification values. Selecting option B as the optimal fit based on linguistic parameters.
+    </think>
+    B. ксефокам
     ```