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

Libraries

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

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

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

Use Docker

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

SGLang

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

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

Automated MNLP evaluation report (2026-06-03)

#14

by zechen-nlp - opened Jun 3

base: refs/heads/main

←

from: refs/pr/14

Discussion Files changed

+22

-14

Files changed (5) hide show

EVAL_REPORT.md +18 -10
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1
model.safetensors +1 -1
tokenizer_config.json +1 -1

EVAL_REPORT.md CHANGED Viewed

@@ -2,7 +2,7 @@
 - **Model repo:** [`cs-552-2026-catma/multilingual_model`](https://huggingface.co/cs-552-2026-catma/multilingual_model)
 - **Owner(s):** group **catma**
-- **Generated at:** 2026-05-28T08:03:33+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 | 0.6500 | ok |
 | Safety | — | not run |
 ## Sample completions
@@ -24,30 +24,38 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
 **Correct** (1 shown)
-- **reference**: `A`
 - **overall** (1/1 completions correct)
-- **extracted** (✓): `A`
 - **completion**:
     ```text
     <think>
-    Analizando las opciones, la respuesta correcta es A.
     </think>
-    \boxed{A}
     ```
 **Incorrect** (1 shown)
-- **reference**: `B`
 - **overall** (0/1 completions correct)
-- **extracted** (✗): `A`
 - **completion**:
     ```text
     <think>
-    विकल्पों का विश्लेषण करते हुए, सही उत्तर A है।
     </think>
-    \boxed{A}
     ```

 - **Model repo:** [`cs-552-2026-catma/multilingual_model`](https://huggingface.co/cs-552-2026-catma/multilingual_model)
 - **Owner(s):** group **catma**
+- **Generated at:** 2026-06-03T00:36:50+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 | 0.4000 | ok |
 | Safety | — | not run |
 ## Sample completions
 **Correct** (1 shown)
+- **reference**: `C`
 - **overall** (1/1 completions correct)
+- **extracted** (✓): `C`
 - **completion**:
     ```text
     <think>
+    检查各个选项：
+    D. 4 — 不正确。
+    A. 20 — 排除。
+    B. 5 — 排除。
+    剩下C，即为正确答案：'100'。
     </think>
+    \boxed{C}
     ```
 **Incorrect** (1 shown)
+- **reference**: `D`
 - **overall** (0/1 completions correct)
+- **extracted** (✗): `C`
 - **completion**:
     ```text
     <think>
+    检查各个选项：
+    B. 没有错，没有错 — 错误。
+    A. 错，错 — 不正确。
+    D. 错，没有错 — 错误。
+    C是唯一正确的选项：'没有错，错'。
     </think>
+    \boxed{C}
     ```

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047823c2605576a4620468c2647befc4f2d375aec5619b0b2944fa9b6fffc974
 size 1981418432

 version https://git-lfs.github.com/spec/v1
+oid sha256:efb889065dae00797c6d1852fec8e1c4f2cab88a6e635723020797748ff7bf89
 size 1981418432

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e37f5d5ec1fa8eb046faeadd024fb7b509bc791420ee4fada4770fa21b740c9
 size 1459766976

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b5c5b6989230b711c6f751cab625f672701ae5fa55b16f132a4fc9d87a6c0f6
 size 1459766976

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e1a2e85a7d6175587f0e8ad7cf78487c1e1689e44b850edd452e28f1b82b6a
 size 3441185608

 version https://git-lfs.github.com/spec/v1
+oid sha256:9979b64f708bad5f18d4ead6f1f0a2f82293f15902356868e36dd2be47a67c18
 size 3441185608

tokenizer_config.json CHANGED Viewed

@@ -20,7 +20,7 @@
     "<|image_pad|>",
     "<|video_pad|>"
   ],
-  "is_local": false,
   "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",

     "<|image_pad|>",
     "<|video_pad|>"
   ],
+  "is_local": true,
   "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",