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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ManhHoDinh/lfm25-titlegen-dpo")
model = AutoModelForCausalLM.from_pretrained("ManhHoDinh/lfm25-titlegen-dpo", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ManhHoDinh/lfm25-titlegen-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ManhHoDinh/lfm25-titlegen-dpo"
# 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-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

ManhHoDinh commited on Aug 16

Commit

7da8035

verified ·

1 Parent(s): 3cccce1

Publish TitleGen benchmark report

Browse files

Files changed (1) hide show

benchmark-report.json +143 -0

benchmark-report.json ADDED Viewed

	@@ -0,0 +1,143 @@

+{
+  "benchmark_revision": "titlegen-local-en-vi-v1",
+  "decoding": {
+    "do_sample": false,
+    "max_new_tokens": 32
+  },
+  "evaluator_revision": "b35cd97518cd",
+  "evidence_level": "PRELIMINARY_AUTOMATED_EN_VI",
+  "languages": {
+    "de": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "en": {
+      "pass_count": 197,
+      "pass_rate": 0.994949,
+      "sample_count": 198,
+      "status": "EVALUATED"
+    },
+    "es": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "fil": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "fr": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "id": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "ja": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "ko": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "lo": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "ms": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "my": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "pt": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "ru": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "ta": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "th": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "NOT_EVALUATED"
+    },
+    "vi": {
+      "pass_count": 96,
+      "pass_rate": 0.941176,
+      "sample_count": 102,
+      "status": "EVALUATED"
+    },
+    "zh": {
+      "pass_count": 0,
+      "pass_rate": 0.0,
+      "sample_count": 0,
+      "status": "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."
+  ],
+  "model": {
+    "key": "dpo",
+    "repo": "ManhHoDinh/lfm25-titlegen-dpo",
+    "revision": "3cccce152745bee40de7dc5cb0c6cefa146bf0a7",
+    "weight_sha256": "4d2eb64fb379c6f6a4d3c059342eea7c6135147ba1146ff03248a095196db192"
+  },
+  "overall": {
+    "pass_count": 293,
+    "pass_rate": 0.976667,
+    "sample_count": 300,
+    "status": "EVALUATED"
+  },
+  "publication_timestamp": "2026-08-16T00:00:00+07:00",
+  "rubric_ids": [
+    "3-8_tu",
+    "khong_cham_cuoi",
+    "mot_dong",
+    "dung_ngon_ngu",
+    "khong_chep"
+  ],
+  "schema_version": "titlegen-public-benchmark.v1",
+  "suite_sha256": {
+    "en": "5381837ade48220be86af0bcf90d863a32c85d1f2f6d4c6bee24f1e7b38830bb",
+    "vi": "6b8d3c8e7a990aa839eccf40f18c5191a618e23d24e2821008003b1ea5c82d43"
+  }
+}