Instructions to use ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16

SGLang

How to use ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 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 "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16" \
    --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": "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16" \
        --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": "ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 with Docker Model Runner:
```
docker model run hf.co/ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16
```

ibrahimkettaneh commited on 16 days ago

Commit

166a8d2

verified ·

1 Parent(s): 090794e

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +21 -0

README.md ADDED Viewed

	@@ -0,0 +1,21 @@

+---
+license: other
+base_model: stepfun-ai/Step-3.7-Flash
+library_name: transformers
+tags:
+- stepfun
+- step-3.7
+- bf16
+- abliteration
+- heretic
+---
+# Step-3.7-Flash-uncensored-abliteratedheretic-bf16
+BF16 Step-3.7-Flash weights modified by gradient-based abliteration of selected `self_attn.o_proj` directions.
+Base model: `stepfun-ai/Step-3.7-Flash`.
+Modification strength: lambda `0.1`.
+Modified layers: text layers 0-44.
+Use according to the base model license/terms.