Instructions to use whitebear33/sn92-ra-v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whitebear33/sn92-ra-v6 with Transformers:

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

pipe = pipeline("text-generation", model="whitebear33/sn92-ra-v6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("whitebear33/sn92-ra-v6")
model = AutoModelForCausalLM.from_pretrained("whitebear33/sn92-ra-v6", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use whitebear33/sn92-ra-v6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whitebear33/sn92-ra-v6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whitebear33/sn92-ra-v6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whitebear33/sn92-ra-v6

SGLang

How to use whitebear33/sn92-ra-v6 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 "whitebear33/sn92-ra-v6" \
    --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": "whitebear33/sn92-ra-v6",
		"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 "whitebear33/sn92-ra-v6" \
        --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": "whitebear33/sn92-ra-v6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use whitebear33/sn92-ra-v6 with Docker Model Runner:
```
docker model run hf.co/whitebear33/sn92-ra-v6
```

sn92-ra-v6

A Jev-compatible specialist model for the REAX (Bittensor subnet 92) risk_assessment track: it answers typed decision questions (choice, noul, score) in one forward pass with the fixed reax-decide-prompt/1 letter readout.

Base model: Qwen/Qwen3.5-9B at revision c202236235762e1c871ad0ccb60c8ee5ba337b9a, text-only (Qwen3_5ForCausalLM: the vision tower and the multi-token-prediction head are removed), 8.95 B parameters, bf16.
Fine-tuned with LoRA (merged) on the public train split of the SN92 specialists dataset and on programmatically generated variations of its procedural task families; output logits scaled by 1.3 (calibration of the T = 2 readout).
Training data credit: "REAX / decisionmodels, SN92 specialists dataset" (CC-BY-4.0).
Licence: Apache-2.0 (see LICENSE).

Downloads last month: 29

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for whitebear33/sn92-ra-v6

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(1132)

this model

whitebear33
/

sn92-ra-v6

sn92-ra-v6

Model tree for whitebear33/sn92-ra-v6

Dataset used to train whitebear33/sn92-ra-v6