Instructions to use nqd145/Gemma-4-E2B-it-abliterated-litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nqd145/Gemma-4-E2B-it-abliterated-litertlm with Transformers:

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

pipe = pipeline("text-generation", model="nqd145/Gemma-4-E2B-it-abliterated-litertlm")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nqd145/Gemma-4-E2B-it-abliterated-litertlm", dtype="auto")

LiteRT-LM

How to use nqd145/Gemma-4-E2B-it-abliterated-litertlm with LiteRT-LM:

# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM)
# and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter).
# For platform-specific integration guides, please refer to the official developer website:
# https://ai.google.dev/edge/litert-lm

# To try LiteRT-LM, the easiest way is to use our CLI tool.
# 1. Install the LiteRT-LM CLI tool:
pip install litert-lm

# 2. Download and run this model locally:
# See: https://ai.google.dev/edge/litert-lm/cli
litert-lm run \
  --from-huggingface-repo=nqd145/Gemma-4-E2B-it-abliterated-litertlm \
  model.litertlm \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nqd145/Gemma-4-E2B-it-abliterated-litertlm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nqd145/Gemma-4-E2B-it-abliterated-litertlm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nqd145/Gemma-4-E2B-it-abliterated-litertlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nqd145/Gemma-4-E2B-it-abliterated-litertlm

SGLang

How to use nqd145/Gemma-4-E2B-it-abliterated-litertlm 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 "nqd145/Gemma-4-E2B-it-abliterated-litertlm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nqd145/Gemma-4-E2B-it-abliterated-litertlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "nqd145/Gemma-4-E2B-it-abliterated-litertlm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nqd145/Gemma-4-E2B-it-abliterated-litertlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nqd145/Gemma-4-E2B-it-abliterated-litertlm with Docker Model Runner:
```
docker model run hf.co/nqd145/Gemma-4-E2B-it-abliterated-litertlm
```

nqd145 commited on Apr 13

Commit

7c778c0

verified ·

1 Parent(s): 966f561

Upload allow_list.json with huggingface_hub

Browse files

Files changed (1) hide show

allow_list.json +31 -0

allow_list.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "name": "Gemma-4-E2B-it-abliterated",
+  "modelId": "nqd145/gemma-4-E2B-it-abliterated-litert-lm",
+  "modelFile": "Gemma-4-E2B-it-abliterated.litertlm",
+  "description": "A LiteRT-LM export of Huihui Gemma 4 E2B it abliterated, ready for on-device deployment with text generation workloads.",
+  "sizeInBytes": 5065244672,
+  "minDeviceMemoryInGb": 8,
+  "commitHash": "581a7e37c3be958673b62c6f43a70247228fa074",
+  "llmSupportImage": false,
+  "llmSupportAudio": false,
+  "llmSupportThinking": true,
+  "defaultConfig": {
+    "topK": 64,
+    "topP": 0.95,
+    "temperature": 1.0,
+    "maxContextLength": 32000,
+    "maxTokens": 4000,
+    "accelerators": "gpu,cpu",
+    "visionAccelerator": "gpu"
+  },
+  "taskTypes": [
+    "llm_chat",
+    "llm_prompt_lab",
+    "llm_agent_chat"
+  ],
+  "bestForTaskTypes": [
+    "llm_chat",
+    "llm_prompt_lab",
+    "llm_agent_chat"
+  ]
+}