Instructions to use SlayerLab/fabryka-english-base-250m-e01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SlayerLab/fabryka-english-base-250m-e01 with Transformers:

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

pipe = pipeline("text-generation", model="SlayerLab/fabryka-english-base-250m-e01", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SlayerLab/fabryka-english-base-250m-e01", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SlayerLab/fabryka-english-base-250m-e01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SlayerLab/fabryka-english-base-250m-e01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SlayerLab/fabryka-english-base-250m-e01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SlayerLab/fabryka-english-base-250m-e01

SGLang

How to use SlayerLab/fabryka-english-base-250m-e01 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 "SlayerLab/fabryka-english-base-250m-e01" \
    --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": "SlayerLab/fabryka-english-base-250m-e01",
		"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 "SlayerLab/fabryka-english-base-250m-e01" \
        --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": "SlayerLab/fabryka-english-base-250m-e01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SlayerLab/fabryka-english-base-250m-e01 with Docker Model Runner:
```
docker model run hf.co/SlayerLab/fabryka-english-base-250m-e01
```

fabryka-english-base-250m-e01

File size: 551 Bytes

1fa0582

{
  "complete": true,
  "int_index": 2.7679707593132328,
  "inputs_percent": {
    "arc_easy": 29.41919191919192,
    "arc_challenge": 23.208191126279864,
    "piqa": 51.4689880304679,
    "hellaswag": 24.965146385182234,
    "arithmark3": 31.3
  },
  "model_revision": "1e9760c8a1cc0a41f2461d49b5f12d7e4148a2d5",
  "formula": "[N(H,25)+N((ARC_E+ARC_C)/2,25)+N(P,50)+0.65*N(A3,25)]/3.65; N(s,c)=100*(s-c)/(100-c)",
  "source": "https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard/blob/d367c542e1278d78779700e34ab740d9dda0f02a/index.html"
}