Instructions to use jacepark12/LFM2.5-2.6B-Terminal-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jacepark12/LFM2.5-2.6B-Terminal-SFT with Transformers:

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

pipe = pipeline("text-generation", model="jacepark12/LFM2.5-2.6B-Terminal-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jacepark12/LFM2.5-2.6B-Terminal-SFT")
model = AutoModelForCausalLM.from_pretrained("jacepark12/LFM2.5-2.6B-Terminal-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 jacepark12/LFM2.5-2.6B-Terminal-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jacepark12/LFM2.5-2.6B-Terminal-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": "jacepark12/LFM2.5-2.6B-Terminal-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jacepark12/LFM2.5-2.6B-Terminal-SFT

SGLang

How to use jacepark12/LFM2.5-2.6B-Terminal-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 "jacepark12/LFM2.5-2.6B-Terminal-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": "jacepark12/LFM2.5-2.6B-Terminal-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 "jacepark12/LFM2.5-2.6B-Terminal-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": "jacepark12/LFM2.5-2.6B-Terminal-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jacepark12/LFM2.5-2.6B-Terminal-SFT with Docker Model Runner:
```
docker model run hf.co/jacepark12/LFM2.5-2.6B-Terminal-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LFM2.5-2.6B Terminal SFT

Full-parameter supervised fine-tuning of LiquidAI/LFM2.5-2.6B for terminal-agent tasks.

The experiment reproduces the Phase 1 configuration in Liquid-CLI's train_unsloth_processed.py, changing only the base model and using native Transformers/TRL FlashAttention support for LFM2.5.

Training data

139,841 non-coding terminal-agent conversations prepared from the skill_based_easy, skill_based_medium, and skill_based_mixed configurations of nvidia/Nemotron-Terminal-Corpus using Liquid-CLI's prepare_data.py.

Training configuration

Full-parameter BF16 fine-tuning
Sequence length: 4,096
Packing: enabled
Assistant-only loss: enabled
Per-device batch size: 4
Gradient accumulation: 32 (effective batch size 128)
Epochs: 1
Learning rate: 2e-5
Optimizer: AdamW 8-bit
Warmup steps: 10
Weight decay: 0.01
Scheduler: linear
Seed: 3407
Attention: FlashAttention 2
Hardware: 1x NVIDIA H100 80GB

Training results

Optimizer steps: 1,092 / 1,092
Final epoch: 1.0
Training loss: 0.2867
Mean token accuracy: 0.8947
Tokens processed: 544,812,939
Training runtime: 34,353 seconds (about 9 hours 33 minutes)

Source

Experiment: https://github.com/gyunggyung/Liquid-CLI
Base model: https://huggingface.co/LiquidAI/LFM2.5-2.6B
Dataset: https://huggingface.co/datasets/nvidia/Nemotron-Terminal-Corpus

Downloads last month: 172

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for jacepark12/LFM2.5-2.6B-Terminal-SFT

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-2.6B

Finetuned

(21)

this model

Quantizations

2 models

jacepark12
/

LFM2.5-2.6B-Terminal-SFT