Instructions to use DruidTheGetafix/apiary-7B-A1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DruidTheGetafix/apiary-7B-A1B with Transformers:

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

pipe = pipeline("text-generation", model="DruidTheGetafix/apiary-7B-A1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DruidTheGetafix/apiary-7B-A1B")
model = AutoModelForCausalLM.from_pretrained("DruidTheGetafix/apiary-7B-A1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DruidTheGetafix/apiary-7B-A1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DruidTheGetafix/apiary-7B-A1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DruidTheGetafix/apiary-7B-A1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DruidTheGetafix/apiary-7B-A1B

SGLang

How to use DruidTheGetafix/apiary-7B-A1B 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 "DruidTheGetafix/apiary-7B-A1B" \
    --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": "DruidTheGetafix/apiary-7B-A1B",
		"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 "DruidTheGetafix/apiary-7B-A1B" \
        --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": "DruidTheGetafix/apiary-7B-A1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DruidTheGetafix/apiary-7B-A1B with Docker Model Runner:
```
docker model run hf.co/DruidTheGetafix/apiary-7B-A1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

apiary-7B-A1B

A 64-expert Mixture-of-Experts language model pretrained from scratch on 9.84B tokens of FineWeb-Edu in 5.24 hours on one 8xB200 node (41.9 B200 GPU-hours). Architecture is exactly Qwen3MoeForCausalLM (16 layers, d=2048, 16/8 heads, 64 experts top-8, expert size 1024, vocab 49152): 6.85B total / 1.21B active parameters. Code, training log and configs: https://github.com/Gaurav-Shah05/apiary

This is a research artifact from a fixed compute budget: it is a coherent base LM in the GPT-2-XL / Pythia-1B class, not an instruction model and not competitive with models trained on trillions of tokens.

Training

Data: first 20 parquet files of HuggingFaceFW/fineweb-edu sample/100BT, tokenized with the SmolLM2 tokenizer (EOS-separated, no document masking), consumed sequentially — see data.py in the code repo.
Optimizer: AdamW lr 3e-4 (betas 0.9/0.95, wd 0.1), 1.05M-token batches, 500 warmup steps, constant then linear decay over the last 20% of the wall-clock budget; grad clip 1.0; load-balance loss 0.01, router z-loss 1e-3.
Systems: PyTorch 2.13, FSDP2 + torch.compile + grouped_mm experts, bf16 with fp32 master weights; median 613k tokens/s (28.2% MFU) on 8xB200; 9382 optimizer steps.
Final train CE 2.497; held-out FineWeb-Edu CE 2.462 (ppl 11.7) on 262k unseen tokens.

Evaluation (lm-eval-harness, 0-shot)

HellaSwag	ARC-e	ARC-c	PIQA	Winogrande	MMLU	wikitext word ppl
48.8	59.6	33.4	70.9	52.5	25.5	19.2

(acc_norm where the task defines it.) Logits parity vs the training code: argmax agreement 90.6%, mean |diff| 0.077.

Provenance

Weights sha256 (first 16 hex): {"model-00001-of-00004.safetensors": "f9266617b050d0fa", "model-00002-of-00004.safetensors": "cf862b24644ea799", "model-00003-of-00004.safetensors": "b09df28b263a22f6", "model-00004-of-00004.safetensors": "7ea4c3d916870908"}. Full per-10-step training log: metrics.jsonl.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for DruidTheGetafix/apiary-7B-A1B

Quantizations

1 model

DruidTheGetafix
/

apiary-7B-A1B

apiary-7B-A1B

Training

Evaluation (lm-eval-harness, 0-shot)

Provenance

Model tree for DruidTheGetafix/apiary-7B-A1B

Dataset used to train DruidTheGetafix/apiary-7B-A1B