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

Libraries

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

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

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

Use Docker

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

SGLang

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

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

zechen-nlp commited on 17 days ago

Commit

c247db0

verified ·

1 Parent(s): b28fb27

Update Automated MNLP evaluation report (2026-05-20)

Browse files

Files changed (1) hide show

EVAL_REPORT.md +7 -25

EVAL_REPORT.md CHANGED Viewed

@@ -2,7 +2,7 @@
 - **Model repo:** [`cs-552-2026-ChatMODS/multilingual_model`](https://huggingface.co/cs-552-2026-ChatMODS/multilingual_model)
 - **Owner(s):** group **ChatMODS**
-- **Generated at:** 2026-05-19T03:22:52+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 | 0.2800 | ok |
 | Safety | — | not run |
 ## Sample completions
@@ -24,40 +24,22 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
 **Correct** (1 shown)
-- **reference**: `C`
 - **overall** (1/1 completions correct)
-- **extracted** (✓): `C`
 - **completion**:
     ```text
-    “自由资本主义时代的‘世界工场’”这一说法通常指的是在18世纪末到19世纪初，资本主义发展过程中，率先实现工业化并成为全球经济中心的国家。
-    在这一时期，**英国**是最早实现工业革命的国家，率先建立了全球最大的工业经济体，成为“世界工场”。因此，正确答案是：
-    $$
-    \boxed{C}
-    $$
     ```
 **Incorrect** (1 shown)
 - **reference**: `D`
 - **overall** (0/1 completions correct)
-- **extracted** (✗): `<no answer>`
 - **completion**:
     ```text
-    Правильный ответ: **D. Индекс качества**
-    **Обоснование:**
-    Индекс качества — это комплексный показатель качества разнородной продукции, который рассчитывается как средний взвешенный относительный показатель качества каждой отдельной продукции. Он учитывает не только уровень качества отдельных продуктов, но и их разнообразие, что делает его подходящим для оценки всей совокупности продукции.
-    Остальные варианты:
-    - **A. Индекс дефектности** — это показатель количества дефектов, а не качества.
-    - **B. Показатель технологичности** — касается технологических процессов, а не качества продукции.
-    - **C. Индекс технологичности** — аналогично B, касается технологической стороны, а не качества.
-    Таким образом, **D. Индекс качества** — правильный ответ.
     ```

 - **Model repo:** [`cs-552-2026-ChatMODS/multilingual_model`](https://huggingface.co/cs-552-2026-ChatMODS/multilingual_model)
 - **Owner(s):** group **ChatMODS**
+- **Generated at:** 2026-05-20T05:49:46+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._
 |---|---:|---|
 | Math | — | not run |
 | Knowledge | — | not run |
+| Multilingual | 0.4500 | ok |
 | Safety | — | not run |
 ## Sample completions
 **Correct** (1 shown)
+- **reference**: `B`
 - **overall** (1/1 completions correct)
+- **extracted** (✓): `B`
 - **completion**:
     ```text
+    \boxed{B}
     ```
 **Incorrect** (1 shown)
 - **reference**: `D`
 - **overall** (0/1 completions correct)
+- **extracted** (✗): `B`
 - **completion**:
     ```text
+    \boxed{B}
     ```