Instructions to use rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP with Transformers:

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

pipe = pipeline("text-generation", model="rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP")
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("rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP")
model = AutoModelForMultimodalLM.from_pretrained("rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP", 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 rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP

SGLang

How to use rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP 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 "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP" \
    --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": "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP",
		"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 "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP" \
        --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": "rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP with Docker Model Runner:
```
docker model run hf.co/rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP
```

Ornith-1.0-35B — PrismaAURA 4.75-bit (mixed NVFP4/FP8/BF16) + MTP

Mixed-precision quantization of deepreinforce-ai/Ornith-1.0-35B via PrismaAURA — per-Linear bit allocation selected on real end-to-end KL, shipped as a stock compressed-tensors checkpoint that vanilla vLLM serves with no forked runtime and no custom kernels. Includes a Multi-Token-Prediction (MTP) head for speculative decoding.

Metric	Value
Effective rate (body)	4.75 bits / quantizable parameter
Size	~23 GB (from ~70 GB BF16)
Served confident KL-vs-BF16	0.0143 (top-1 agreement 98.6%)
MTP acceptance	91.3% @ pos-0, 77.3% overall (~2.32 accepted / 3 drafted)
Serving	vanilla vLLM, CUTLASS native NVFP4 W4A4 on Blackwell

MTP note

The base Ornith checkpoint ships no MTP weights (the fine-tune stripped them). This artifact grafts the base Qwen3.5-35B-A3B MTP head (BF16), the same head every community MTP-Ornith variant uses. Because it predicts the base distribution rather than Ornith's RL-tuned one, acceptance is a bit lower than a native head would give — but still strong (91% at position 0).

Serving

With speculative decoding (MTP):

vllm serve rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP \
  --trust-remote-code --attention-backend flashinfer --moe-backend marlin \
  --gpu-memory-utilization 0.85 --max-model-len 32768 --max-num-batched-tokens 8192 \
  --enable-chunked-prefill \
  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'

Without MTP (e.g. for clean perplexity measurement — spec-decode poisons logprob metrics), drop the --speculative-config flag. --max-num-batched-tokens >= 2096 is required (Gated-DeltaNet page size).

License

Inherits the base model's license — see deepreinforce-ai/Ornith-1.0-35B.

Contact

Robert Tand — [email protected]

Downloads last month: 11,679

Safetensors

Model size

22B params

Tensor type

F32

BF16

F8_E4M3

Model tree for rdtand/Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP

Base model

ornith-ai/Ornith-1.0-35B

Quantized

(172)

this model