Instructions to use KoarAI/LFM2.5-350M-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoarAI/LFM2.5-350M-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="KoarAI/LFM2.5-350M-Thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoarAI/LFM2.5-350M-Thinking")
model = AutoModelForCausalLM.from_pretrained("KoarAI/LFM2.5-350M-Thinking", 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 KoarAI/LFM2.5-350M-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoarAI/LFM2.5-350M-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoarAI/LFM2.5-350M-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KoarAI/LFM2.5-350M-Thinking

SGLang

How to use KoarAI/LFM2.5-350M-Thinking 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 "KoarAI/LFM2.5-350M-Thinking" \
    --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": "KoarAI/LFM2.5-350M-Thinking",
		"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 "KoarAI/LFM2.5-350M-Thinking" \
        --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": "KoarAI/LFM2.5-350M-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KoarAI/LFM2.5-350M-Thinking with Docker Model Runner:
```
docker model run hf.co/KoarAI/LFM2.5-350M-Thinking
```

KoarAI commited on about 14 hours ago

Commit

ea15434

verified ·

1 Parent(s): d01ea0a

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -38,9 +38,9 @@ library_name: transformers
 > [!IMPORTANT]
 > **Model Code:** `0002`
-> Эта версия модели подверглась глубокому переобучению всех 100% весов (Full Weight Retraining) на 9 эпох с косинусным затуханием, интеграцией расширенного мульти-датасета (Reasoning CoT + DeepSeek Agentic + MMLU-Pro + AIME 2026) и строгой синтаксической нормализацией тегов `<think>`.
 >
-> 🚀 **Политика версионирования KoarAI:** Начиная со следующего релиза (`0003` и далее), вместо перезаписи текущего репозитория для каждой новой итерации будут создаваться **отдельные независимые репозитории** (например, `KoarAI/LFM2.5-350M-Thinking-v3` / `...-RU` и т.д.).
 ---

 > [!IMPORTANT]
 > **Model Code:** `0002`
+> This version underwent a comprehensive 100% Full Parameter Fine-Tuning across **9 epochs** with a cosine learning rate scheduler. It integrates an expanded multi-teacher dataset (Reasoning CoT + DeepSeek-V4-Pro Agentic + MMLU-Pro + AIME 2026 Mathematics) and strict syntactic normalization for `<think> ... </think>` blocks.
 >
+> 🚀 **KoarAI Release & Versioning Policy:** Starting from the upcoming release (`0003` and beyond), rather than overwriting existing models, each new iteration will be released into its own **dedicated repository** (e.g., `KoarAI/LFM2.5-350M-Thinking-v3`, `KoarAI/LFM2.5-350M-Thinking-RU`, etc.).
 ---