Instructions to use heterodoxin/gemma-4-e4b-it-apostate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heterodoxin/gemma-4-e4b-it-apostate with Transformers:

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

pipe = pipeline("text-generation", model="heterodoxin/gemma-4-e4b-it-apostate")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("heterodoxin/gemma-4-e4b-it-apostate")
model = AutoModelForMultimodalLM.from_pretrained("heterodoxin/gemma-4-e4b-it-apostate", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use heterodoxin/gemma-4-e4b-it-apostate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heterodoxin/gemma-4-e4b-it-apostate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heterodoxin/gemma-4-e4b-it-apostate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/heterodoxin/gemma-4-e4b-it-apostate

SGLang

How to use heterodoxin/gemma-4-e4b-it-apostate 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 "heterodoxin/gemma-4-e4b-it-apostate" \
    --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": "heterodoxin/gemma-4-e4b-it-apostate",
		"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 "heterodoxin/gemma-4-e4b-it-apostate" \
        --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": "heterodoxin/gemma-4-e4b-it-apostate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use heterodoxin/gemma-4-e4b-it-apostate with Docker Model Runner:
```
docker model run hf.co/heterodoxin/gemma-4-e4b-it-apostate
```

gemma-4-e4b-it-apostate / apostate_config.json

heterodoxin

Upload folder using huggingface_hub

d02c391 verified 3 months ago

Raw

History Blame Contribute Delete

4.11 kB

	{
	"model": "google/gemma-4-e4b-it",
	"output_dir": "/var/home/Heterodoxin/gemma_resp_D",
	"profile": "balanced",
	"device": "cuda",
	"load_in_4bit": true,
	"cpu_offload_gb": 0.0,
	"compute_dtype": "bfloat16",
	"seed": 0,
	"resume": false,
	"cache_activations": true,
	"activation_cache_dir": null,
	"harmful_path": "mlabonne/harmful_behaviors:train:text\|/var/home/Heterodoxin/apostate/data/harmful.txt\|/var/home/Heterodoxin/apostate/data/refusal_calibration.txt",
	"harmless_path": "mlabonne/harmless_alpaca:train:text\|/var/home/Heterodoxin/apostate/data/harmless.txt",
	"harmful_test": "mlabonne/harmful_behaviors:test:text\|JailbreakBench/JBB-Behaviors@behaviors:harmful:Goal\|/var/home/Heterodoxin/apostate/data/refusal_calibration.txt",
	"harmless_test": "mlabonne/harmless_alpaca:test:text",
	"refusal_eval_path": "JailbreakBench/JBB-Behaviors@behaviors:harmful:Goal\|/var/home/Heterodoxin/apostate/data/refusal_calibration.txt",
	"refusal_eval_n": 64,
	"kl_eval_path": "mlabonne/harmless_alpaca:test:text",
	"kl_eval_n": 48,
	"preserve_path": null,
	"n_harmful": 600,
	"n_harmless": 600,
	"n_eval": 128,
	"max_new_tokens": 256,
	"batch_size": 48,
	"baseline_eval_n": 24,
	"head_sweep": true,
	"head_sweep_min": 3.5,
	"head_sweep_max": 5.5,
	"head_sweep_step": 0.5,
	"head_sweep_top_k": 6,
	"head_sweep_probe_n": 8,
	"head_sweep_eval_n": 48,
	"head_sweep_probe_classifier": false,
	"fit_response_activations": true,
	"fit_response_n": 160,
	"fit_response_tokens": 32,
	"refusal_rank": 1,
	"variance_threshold": 0.9,
	"max_rank": 3,
	"direction_layer_frac": 0.6,
	"direction_scope": "global",
	"multi_refusal": true,
	"multi_refusal_clusters": 6,
	"multi_refusal_min_norm": 0.08,
	"multi_refusal_min_separation": 0.05,
	"multi_refusal_min_coverage": 0.05,
	"orthogonalize_direction": true,
	"causal_targeting": true,
	"causal_floor": 0.1,
	"causal_temperature": 1.0,
	"preserve_rank": 8,
	"refine_refusal": true,
	"refine_max_scale": 2.0,
	"refine_steps": 6,
	"refine_deescalate": true,
	"refine_kl_steps": 10,
	"refine_scale_rerank_k": 2,
	"refine_kl_layer_steps": 10,
	"refine_kl_layer_candidates": 8,
	"repair_steps": 4,
	"repair_candidates": 8,
	"repair_rerank_k": 5,
	"repair_probe_candidates": 20,
	"repair_probe_ref_n": 12,
	"repair_probe_kl_n": 16,
	"repair_probe_positions": 8,
	"repair_refusal_regress_slack": 0.01,
	"repair_stop_kl_frac": 0.8,
	"repair_min_alpha": 0.001,
	"repair_min_kl_gain": 0.003,
	"repair_min_refusal_gain": 0.005,
	"repair_min_score_gain": 0.01,
	"repair_eval_n": 96,
	"repair_kl_n": 64,
	"refine_refusal_slack": 0.01,
	"final_zero_trim": false,
	"final_push_bake_margin": 0.075,
	"guard_max_iters": 2,
	"guard_leakage_eps": 0.15,
	"guard_alpha_step": 0.25,
	"optimize": true,
	"n_trials": 16,
	"adaptive_trials": true,
	"kl_weight": 6.0,
	"kl_target": 0.3,
	"kl_target_weight": 18.0,
	"kl_quad_weight": 22.0,
	"kl_headroom_weight": 0.0,
	"kl_over_budget_weight": 72.0,
	"refusal_target_weight": 4.0,
	"refusal_quad_weight": 8.0,
	"kl_positions": 8,
	"opt_capability": true,
	"opt_capability_weight": 2.5,
	"opt_capability_code_n": 8,
	"opt_capability_math_n": 8,
	"opt_eval_n": 64,
	"opt_gen_tokens": 256,
	"eval_denoising_steps": 8,
	"opt_objective": "generation",
	"opt_rerank_k": 5,
	"opt_guard": true,
	"opt_early_stop": true,
	"opt_early_stop_margin": 0.02,
	"gemma_ple": false,
	"gemma_query": false,
	"ple_max_rank": 2,
	"prune": false,
	"prune_max_frac": 0.25,
	"prune_kl": 0.04,
	"max_kl": 0.12,
	"target_refusal": 0.0,
	"oblique_ablation": true,
	"oblique_strength": 1.0,
	"oblique_denom_floor": 0.2,
	"oblique_writers_only": true,
	"oblique_predictive": true,
	"predictive_ridge": 0.01,
	"oblique_preserve": 1.0,
	"oblique_contrast": 1.0,
	"reader_max_kl": 0.55,
	"reader_kl_target": 0.3,
	"reader_strengths": [
	2.0,
	2.5,
	2.75,
	3.0,
	4.0,
	5.0
	],
	"reader_fast_proxy": true,
	"reader_guard_rank": 3,
	"reader_margin_target": -1.0,
	"reader_strength_kl_weight": 1.0,
	"save_dtype": "bfloat16",
	"bake": true
	}