Instructions to use nassimjp/LFM2.5-1.2B-Base-Pashto with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nassimjp/LFM2.5-1.2B-Base-Pashto with Transformers:

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

pipe = pipeline("text-generation", model="nassimjp/LFM2.5-1.2B-Base-Pashto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nassimjp/LFM2.5-1.2B-Base-Pashto")
model = AutoModelForCausalLM.from_pretrained("nassimjp/LFM2.5-1.2B-Base-Pashto", 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 nassimjp/LFM2.5-1.2B-Base-Pashto with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nassimjp/LFM2.5-1.2B-Base-Pashto"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nassimjp/LFM2.5-1.2B-Base-Pashto",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nassimjp/LFM2.5-1.2B-Base-Pashto

SGLang

How to use nassimjp/LFM2.5-1.2B-Base-Pashto 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 "nassimjp/LFM2.5-1.2B-Base-Pashto" \
    --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": "nassimjp/LFM2.5-1.2B-Base-Pashto",
		"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 "nassimjp/LFM2.5-1.2B-Base-Pashto" \
        --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": "nassimjp/LFM2.5-1.2B-Base-Pashto",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nassimjp/LFM2.5-1.2B-Base-Pashto with Docker Model Runner:
```
docker model run hf.co/nassimjp/LFM2.5-1.2B-Base-Pashto
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

2️⃣ TOKENIZER

# ======================================================
# 2️⃣ TOKENIZER
# ======================================================
PASHTO_ATOMS = ["ښ","څ","ځ","ڼ","ږ","ډ","ټ","ړ","ئ","ې","ۍ","ګ",
                "ک","ی","گ","چ","ژ","پ","ۀ","أ","إ","آ","ؤ","ء","ٱ",
                "ٹ","ڈ","ڑ","ں","ھ","ے","ۓ","۰","۱","۲","۳","۴","۵","۶","۷","۸","۹"]

Training Requirements

Continued Pretraining (CPT)

Requires large‑scale Pashto corpora, deduped and domain‑balanced.

Supervised Fine‑Tuning (SFT)

Requires high‑quality Pashto instruction datasets in chat format.

Thanks

Special thanks to the open‑source community and Pashto NLP contributors whose work made this model possible.

Citation

@article{liquidai2025lfm2,
  title={LFM2 Technical Report},
  author={Liquid AI},
  journal={arXiv preprint arXiv:2511.23404},
  year={2025}
}

📄 License

This model is released under the same license terms as the base model (LiquidAI/LFM2.5-1.2B-Base).
Please refer to the original model card for detailed license information.