Instructions to use DreamFast/Gemma4-e4b-abliterlitics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFast/Gemma4-e4b-abliterlitics with Transformers:

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

pipe = pipeline("text-generation", model="DreamFast/Gemma4-e4b-abliterlitics")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DreamFast/Gemma4-e4b-abliterlitics", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DreamFast/Gemma4-e4b-abliterlitics with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DreamFast/Gemma4-e4b-abliterlitics"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DreamFast/Gemma4-e4b-abliterlitics",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DreamFast/Gemma4-e4b-abliterlitics

SGLang

How to use DreamFast/Gemma4-e4b-abliterlitics 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 "DreamFast/Gemma4-e4b-abliterlitics" \
    --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": "DreamFast/Gemma4-e4b-abliterlitics",
		"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 "DreamFast/Gemma4-e4b-abliterlitics" \
        --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": "DreamFast/Gemma4-e4b-abliterlitics",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DreamFast/Gemma4-e4b-abliterlitics with Docker Model Runner:
```
docker model run hf.co/DreamFast/Gemma4-e4b-abliterlitics
```

Gemma4-e4b-abliterlitics / results /base_to_coder3101_keys.csv

DreamFast

Upload results/base_to_coder3101_keys.csv with huggingface_hub

37b177f verified 9 days ago

Raw

History Blame Contribute Delete

1.66 kB

	tensor,mean_abs_diff
	model.language_model.layers.31.self_attn.o_proj.weight,0.0008527684840373695
	model.language_model.layers.25.self_attn.o_proj.weight,0.0005986130563542247
	model.language_model.layers.24.self_attn.o_proj.weight,0.0005704322247765958
	model.language_model.layers.34.self_attn.o_proj.weight,0.0005669129313901067
	model.language_model.layers.30.self_attn.o_proj.weight,0.000554397702217102
	model.language_model.layers.39.self_attn.o_proj.weight,0.0005324308876879513
	model.language_model.layers.32.self_attn.o_proj.weight,0.0005121523281559348
	model.language_model.layers.38.self_attn.o_proj.weight,0.0005104857264086604
	model.language_model.layers.26.self_attn.o_proj.weight,0.0005002946709282696
	model.language_model.layers.27.self_attn.o_proj.weight,0.0004930723225697875
	model.language_model.layers.22.self_attn.o_proj.weight,0.0004693045630119741
	model.language_model.layers.33.self_attn.o_proj.weight,0.00046057128929533064
	model.language_model.layers.40.self_attn.o_proj.weight,0.00042951255454681814
	model.language_model.layers.36.self_attn.o_proj.weight,0.0004277386178728193
	model.language_model.layers.28.self_attn.o_proj.weight,0.0004223079886287451
	model.language_model.layers.37.self_attn.o_proj.weight,0.0004189459141343832
	model.language_model.layers.21.self_attn.o_proj.weight,0.0003818950499407947
	model.language_model.layers.29.self_attn.o_proj.weight,0.00035143602872267365
	model.language_model.layers.23.self_attn.o_proj.weight,0.00027919490821659565
	model.language_model.layers.35.self_attn.o_proj.weight,0.00019251968478783965
	model.language_model.layers.41.self_attn.o_proj.weight,8.739201803109609e-06