Instructions to use Calandracas/minnow-pico-50M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Calandracas/minnow-pico-50M-base with Transformers:

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

pipe = pipeline("text-generation", model="Calandracas/minnow-pico-50M-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Calandracas/minnow-pico-50M-base")
model = AutoModelForCausalLM.from_pretrained("Calandracas/minnow-pico-50M-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Calandracas/minnow-pico-50M-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Calandracas/minnow-pico-50M-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Calandracas/minnow-pico-50M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Calandracas/minnow-pico-50M-base

SGLang

How to use Calandracas/minnow-pico-50M-base 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 "Calandracas/minnow-pico-50M-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Calandracas/minnow-pico-50M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Calandracas/minnow-pico-50M-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Calandracas/minnow-pico-50M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Calandracas/minnow-pico-50M-base with Docker Model Runner:
```
docker model run hf.co/Calandracas/minnow-pico-50M-base
```

minnow-pico-50M-base

A 48.5M parameter DeepSeek-V4 architecture model trained from scratch on a multilingual blend of C4 data (108 languages). This is a research sandbox model for studying the DeepSeek-V4 architecture at small scale — it is not a production model and has no practical use.

Architecture

Based on the DeepSeek-V4 architecture, consumed via HuggingFace DeepseekV4ForCausalLM (transformers ≥ 5.14):

256-dim hidden, 8 layers, 4 heads × 64 head_dim
16 experts, top-2 routing (Sqrt(Softplus) affinity)
Hash-routed MoE on first 3 layers, learned routing on last 2
Hybrid attention (CSA + HCA + sliding)
Manifold-Constrained Hyper-Connections (mHC)
Grouped low-rank attention output projection
48,538,724 parameters total

Training

Data: 1B tokens from a multilingual C4 blend (108 languages)
Optimizer: AdamW (betas 0.9, 0.95)
Learning rate: 6e-4, cosine schedule, 763 warmup steps
Batch size: 131,072 tokens/step (2× RX 7900 XTX, NCCL DDP)
Steps: 7,629
Final loss: 3.49
Hardware: 2× AMD RX 7900 XTX (gfx1100, RDNA3)

This model was trained from scratch (random initialization) — it does not inherit weights from any pretrained model.

Tokenizer

Uses the DeepSeek-V4-Flash-0731 tokenizer (vocab 129,280).

Disclaimer

This model exists purely for architectural experimentation. At 48.5M parameters, it cannot perform any useful tasks. Do not use it for anything.

Downloads last month: 282

Safetensors

Model size

49.3M params

Tensor type

I64

F32

BF16

Paper for Calandracas/minnow-pico-50M-base

Damping of Fast Radio Bursts in the Inner Magnetospheres of Magnetars

Paper • 2606.19448 • Published Jun 17