Instructions to use Blockway/Agens-Volundr-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blockway/Agens-Volundr-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="Blockway/Agens-Volundr-tiny-random")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Blockway/Agens-Volundr-tiny-random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Blockway/Agens-Volundr-tiny-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Blockway/Agens-Volundr-tiny-random

SGLang

How to use Blockway/Agens-Volundr-tiny-random 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 "Blockway/Agens-Volundr-tiny-random" \
    --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": "Blockway/Agens-Volundr-tiny-random",
		"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 "Blockway/Agens-Volundr-tiny-random" \
        --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": "Blockway/Agens-Volundr-tiny-random",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Blockway/Agens-Volundr-tiny-random with Docker Model Runner:
```
docker model run hf.co/Blockway/Agens-Volundr-tiny-random
```

Agens-Volundr-tiny-random

Random weights, for CI only. This checkpoint produces no meaningful text.

A 4-layer Agens Volundr (2 KDA + 1 BCSA + 1 dense attention, Engram on layer 1, 4-stream mHC) with the same config schema, tokenizer, chat template and generation config as Blockway/Agens-Volundr-32B-v1. Hidden size 64; BCSA window 64, so short prompts reach the far field. Weights are the reference implementation's random initialisation (seed 0). Used by the SGLang Volundr tests. The reference transformers implementation is not included here; it ships with Blockway/Agens-Volundr-32B-v1.

Downloads last month: 25

Safetensors

Model size

32.8M params

Tensor type

BF16