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 31

Commit

2ad0453

verified ·

1 Parent(s): 79cbf36

mirror 0.8.7: control-twin isolation (AlephLLM@b472815)

Browse files

Files changed (1) hide show

presets.py +13 -1

presets.py CHANGED Viewed

@@ -218,10 +218,22 @@ for _name in list(PRESETS):
     _m = AlephLMConfig.from_dict(_p.model.to_dict())
     _m.name = _name + "-control"
     _m.hub_layers = ()
     PRESETS[_name + "-control"] = Preset(
-        model=_m, train=_p.train,
         curriculum=[dict(x) for x in _p.curriculum])
 def get_preset(name: str) -> Preset:
     if name not in PRESETS:

     _m = AlephLMConfig.from_dict(_p.model.to_dict())
     _m.name = _name + "-control"
     _m.hub_layers = ()
+    # 0.8.7: twins get their OWN TrainConfig copy — the shared-instance
+    # form let treatment-specific flags leak into controls (2s-control
+    # inherited head_addr_frozen=True, a post-revival flag no control's
+    # birth recipe may carry) and made cross-mutation possible.
+    _t = TrainConfig(**{k: getattr(_p.train, k)
+                        for k in _p.train.__dataclass_fields__})
     PRESETS[_name + "-control"] = Preset(
+        model=_m, train=_t,
         curriculum=[dict(x) for x in _p.curriculum])
+# The 2s architecture control runs the BIRTH recipe verbatim: born-null
+# unfrozen head (it buries, as the treatment's did for its first 24,860
+# steps — measured 3/3; the +0.01 head term is immaterial at the ±3.4
+# hub scale this control exists to judge).
+PRESETS["mini-beatrix-2s-control"].train.head_addr_frozen = False
 def get_preset(name: str) -> Preset:
     if name not in PRESETS: