Instructions to use AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16")
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("AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16")
model = AutoModelForMultimodalLM.from_pretrained("AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16", 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 AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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": "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16

SGLang

How to use AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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 "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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": "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16",
		"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 "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-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": "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 with Docker Model Runner:
```
docker model run hf.co/AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16
```

AEON-7 commited on 21 days ago

Commit

7ddff52

verified ·

1 Parent(s): e80047d

Recipe: gpu-util 0.6-0.7 on DGX Spark unified memory (>~0.8 thrashes the shared pool); discrete VRAM unchanged

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -68,7 +68,7 @@ A measured, validate-before-ship abliteration:
 ```bash
 vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 \
   --served-model-name ornith --max-model-len 262144 \
-  --gpu-memory-utilization 0.85 --max-num-batched-tokens 16384 \
   --mamba-cache-dtype float32 \
   --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder \
   --limit-mm-per-prompt '{"image":4,"video":2}' --mm-encoder-tp-mode data \
@@ -76,6 +76,7 @@ vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 \
   --enable-chunked-prefill --enable-prefix-caching --trust-remote-code
 ```
 `--served-model-name` takes a list of aliases — name it after the model your clients already request for a drop-in cutover.
 Reasoning model: every turn opens `<think>…</think>`. Recommended sampling: `temperature 0.6, top_p 0.95, top_k 20`. Vision (image/video) is inherited from the base and intact; on a vision-enabled deploy, KV cache stays BF16.
 ## Variants & quantization

 ```bash
 vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 \
   --served-model-name ornith --max-model-len 262144 \
+  --gpu-memory-utilization 0.70 --max-num-batched-tokens 16384 \
   --mamba-cache-dtype float32 \
   --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder \
   --limit-mm-per-prompt '{"image":4,"video":2}' --mm-encoder-tp-mode data \
   --enable-chunked-prefill --enable-prefix-caching --trust-remote-code
 ```
 `--served-model-name` takes a list of aliases — name it after the model your clients already request for a drop-in cutover.
+On the DGX Spark's unified memory keep `--gpu-memory-utilization` at 0.6-0.7; above ~0.8 the shared CPU+GPU pool page-thrashes. Discrete-VRAM GPUs can run higher.
 Reasoning model: every turn opens `<think>…</think>`. Recommended sampling: `temperature 0.6, top_p 0.95, top_k 20`. Vision (image/video) is inherited from the base and intact; on a vision-enabled deploy, KV cache stays BF16.
 ## Variants & quantization