Instructions to use AbstractPhil/mini-beatrix-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbstractPhil/mini-beatrix-1 with Transformers:

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

pipe = pipeline("text-generation", model="AbstractPhil/mini-beatrix-1", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AbstractPhil/mini-beatrix-1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AbstractPhil/mini-beatrix-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbstractPhil/mini-beatrix-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbstractPhil/mini-beatrix-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AbstractPhil/mini-beatrix-1

SGLang

How to use AbstractPhil/mini-beatrix-1 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 "AbstractPhil/mini-beatrix-1" \
    --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": "AbstractPhil/mini-beatrix-1",
		"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 "AbstractPhil/mini-beatrix-1" \
        --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": "AbstractPhil/mini-beatrix-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AbstractPhil/mini-beatrix-1 with Docker Model Runner:
```
docker model run hf.co/AbstractPhil/mini-beatrix-1
```

AbstractPhil commited on Aug 26

Commit

34d7ec4

verified ·

1 Parent(s): 943c0c2

mirror 0.7.4: mini-beatrix-2 hub_chunk 1024 (AlephLLM@cb7cb86)

Browse files

Files changed (1) hide show

presets.py +6 -1

presets.py CHANGED Viewed

@@ -163,7 +163,12 @@ PRESETS: dict[str, Preset] = {
                             hub_layers=tuple(range(32)),
                             hub_K=256, hub_D=256, hub_const=16,
                             bank_experts=6, bank_ff=1024,
-                            head_K=256, head_D=256, hub_chunk=256,
                             hub_ckpt=2),
         train=TrainConfig(micro_batch=4, grad_accum=16,
                           governor="minsep", governor_theta=45.0),

                             hub_layers=tuple(range(32)),
                             hub_K=256, hub_D=256, hub_const=16,
                             bank_experts=6, bank_ff=1024,
+                            # chunk 1024 MEASURED on the mission card (C2e,
+                            # Blackwell 2026-08-26): 72.2 vs 83.2 ms/layer
+                            # fwd+bwd at chunk 256, peak 39.4 -> 26.6 GB.
+                            # S/P traffic ~ 1/C, att work ~ C; config-only,
+                            # checkpoint-compatible, exactness C-independent.
+                            head_K=256, head_D=256, hub_chunk=1024,
                             hub_ckpt=2),
         train=TrainConfig(micro_batch=4, grad_accum=16,
                           governor="minsep", governor_theta=45.0),