Instructions to use ManhHoDinh/lfm25-titlegen-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ManhHoDinh/lfm25-titlegen-sft with Transformers:

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

pipe = pipeline("text-generation", model="ManhHoDinh/lfm25-titlegen-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ManhHoDinh/lfm25-titlegen-sft")
model = AutoModelForCausalLM.from_pretrained("ManhHoDinh/lfm25-titlegen-sft", 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 ManhHoDinh/lfm25-titlegen-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ManhHoDinh/lfm25-titlegen-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ManhHoDinh/lfm25-titlegen-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ManhHoDinh/lfm25-titlegen-sft

SGLang

How to use ManhHoDinh/lfm25-titlegen-sft 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 "ManhHoDinh/lfm25-titlegen-sft" \
    --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": "ManhHoDinh/lfm25-titlegen-sft",
		"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 "ManhHoDinh/lfm25-titlegen-sft" \
        --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": "ManhHoDinh/lfm25-titlegen-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ManhHoDinh/lfm25-titlegen-sft with Docker Model Runner:
```
docker model run hf.co/ManhHoDinh/lfm25-titlegen-sft
```

LFM2.5 TitleGen SFT v2

This model is the supervised fine-tuning stage of the LFM2.5 TitleGen experiment. Model repository: ManhHoDinh/lfm25-titlegen-sft. Benchmark publication timestamp: 2026-08-16T00:00:00+07:00.

Preliminary benchmark

The current model passed 291 of 300 evaluated English and Vietnamese examples (97.0%).

Model	Passed	Overall	English	Vietnamese	Evidence
DPO	293 / 300	97.7%	99.5%	94.1%	Preliminary automated EN/VI
SFT v2	291 / 300	97.0%	99.5%	92.2%	Preliminary automated EN/VI
Curriculum	289 / 300	96.3%	98.5%	92.2%	Preliminary automated EN/VI

Language coverage

Language	Samples	Passed	Rate	Status
German	0	0	0.0%	NOT_EVALUATED
English	198	197	99.5%	EVALUATED
Spanish	0	0	0.0%	NOT_EVALUATED
Filipino	0	0	0.0%	NOT_EVALUATED
French	0	0	0.0%	NOT_EVALUATED
Indonesian	0	0	0.0%	NOT_EVALUATED
Japanese	0	0	0.0%	NOT_EVALUATED
Korean	0	0	0.0%	NOT_EVALUATED
Lao	0	0	0.0%	NOT_EVALUATED
Malay	0	0	0.0%	NOT_EVALUATED
Burmese	0	0	0.0%	NOT_EVALUATED
Portuguese	0	0	0.0%	NOT_EVALUATED
Russian	0	0	0.0%	NOT_EVALUATED
Tamil	0	0	0.0%	NOT_EVALUATED
Thai	0	0	0.0%	NOT_EVALUATED
Vietnamese	102	94	92.2%	EVALUATED
Chinese	0	0	0.0%	NOT_EVALUATED

0 means no evaluated examples when the status is NOT_EVALUATED; it is not a measured zero score.

Methodology

This preliminary benchmark evaluates aggregate English and Vietnamese results with deterministic decoding (do_sample: false, max_new_tokens: 32). Automated rubric identifiers: 3-8_tu, khong_cham_cuoi, mot_dong, dung_ngon_ngu, khong_chep. The remaining contracted languages are shown explicitly as not evaluated.

Limitations

Only English and Vietnamese have evaluated examples.
Language correctness uses an automated heuristic.
No native review or blind preference evidence is included.
These aggregate automated results do not establish production readiness, causal improvement, or statistical significance.

Machine-readable results

See benchmark-report.json for the validated aggregate report.

Downloads last month: 227

Safetensors

Model size

0.2B params

Tensor type

BF16

Model tree for ManhHoDinh/lfm25-titlegen-sft

Base model

LiquidAI/LFM2.5-230M-Base

Finetuned

LiquidAI/LFM2.5-230M

Finetuned

(36)

this model