Instructions to use LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch with Transformers:

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

pipe = pipeline("text-generation", model="LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch")
model = AutoModelForCausalLM.from_pretrained("LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch")
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

vLLM

How to use LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch

SGLang

How to use LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch 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 "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch" \
    --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": "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch",
		"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 "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch" \
        --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": "LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch with Docker Model Runner:
```
docker model run hf.co/LLM-OS-Models/gemma-4-E4B-Terminal-SFT-Native-Liquid-1Epoch
```

gyung commited on 14 days ago

Commit

c021c56

verified ·

1 Parent(s): da82960

Update model card with corrected TB2-lite evaluation

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ base_model: google/gemma-4-E4B
 - Base model: `google/gemma-4-E4B`
 - Training setup: `1 epoch, Gemma native Liquid preprocessing`
-- Evaluation snapshot: `2026-05-09 00:39:32 UTC`
 - Evaluation result id: `gemma4_e4b_base_native_e1`
 ## Quickstart
@@ -159,7 +159,7 @@ python tb2_lite/scripts/replay_eval.py \
 평가는 corrected TB2-lite replay set에서 vLLM으로 수행했습니다. 순위 점수는 `100 * avg_command_f1`만 사용하고, `first_cmd_exact_pct`는 보조 지표로만 봅니다.
-- Rank: `4 / 5`
 - Score: `12.80`
 - Command F1: `0.1280`
 - Command precision: `0.1792`
@@ -172,7 +172,7 @@ python tb2_lite/scripts/replay_eval.py \
 - Template status: `model_specific_or_mixed`
 - Rank eligible: `True`
 - Eval timestamp: `2026-05-09T00:29:29.036507`
-- 현재 집계된 평가 결과 수: `5`
 Prompt/template audit:

 - Base model: `google/gemma-4-E4B`
 - Training setup: `1 epoch, Gemma native Liquid preprocessing`
+- Evaluation snapshot: `2026-05-10 13:03:36 UTC`
 - Evaluation result id: `gemma4_e4b_base_native_e1`
 ## Quickstart
 평가는 corrected TB2-lite replay set에서 vLLM으로 수행했습니다. 순위 점수는 `100 * avg_command_f1`만 사용하고, `first_cmd_exact_pct`는 보조 지표로만 봅니다.
+- Rank: `7 / 8`
 - Score: `12.80`
 - Command F1: `0.1280`
 - Command precision: `0.1792`
 - Template status: `model_specific_or_mixed`
 - Rank eligible: `True`
 - Eval timestamp: `2026-05-09T00:29:29.036507`
+- 현재 집계된 평가 결과 수: `8`
 Prompt/template audit: