Instructions to use paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048 with Transformers:

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

pipe = pipeline("text-generation", model="paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048

SGLang

How to use paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048 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 "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048 with Docker Model Runner:
```
docker model run hf.co/paulzy/lact-1b-p24-1-explicit-all-one-gtcf-on-soft-z001-step-2048
```

LaCT 1B p24-1 explicit-all-one GTCF-ON, z=0.001, step 2048

This public repository is a weights-only archival release of the exact seed-42 terminal step-2048 checkpoint. The checkpoint uses the historical explicit all-one read/update gates in the unrouted prefix while retaining the current K/V-only projection, corrected variable-length boundaries, and exact frozen-head CE path.

The scientific configuration is GTCF-ON with a stop-gradient full-depth teacher, router_eff_coeff=0.5, router_z_coeff=0.001, exit_ce_loss_coeff=0.5, rank-128 SiLU exit adapters, max-pooled router features, and native binary EXIT/CONTINUE argmax routing. Training used sequence length 65,536, gradient accumulation 4, 2,048 steps, a 512-step readout-only first stage, and seed 42.

model.safetensors is 4,381,433,160 bytes with SHA-256 0fc65049d48747c8f1d52dd83ff38f2333f2e1855da335dafc3d13bf06f5b3dc. It contains 542 F32 tensors, including all 20 router tensors, 10 exit-adapter tensors, and 5 exit-norm tensors. The export was produced directly from the complete nine-file full-state step-2048 DCP and passed the project's exact config guard and from_pretrained router-state load guard.

This repository intentionally excludes optimizer and data-iterator state, evaluation predictions/targets/samples, internal operational paths, and tokenizer bytes. Use the matching LaCT implementation in yuan_ttt and the tokenizer from the compatible LaCT base checkpoint (BOS 128000, EOS 128009, vocabulary 128256).

Training completed successfully. NIAH-1, LongBenchV2, and PG-19 also completed, but this archive does not claim a complete five-suite paper result until the separate NIAH-2/3 recovery is admitted. No evaluation samples are published here.

See provenance/ for the public scientific/router contract, source attestation, tensor inventory, and payload checksums.

Downloads last month: 10

Safetensors

Model size

1B params

Tensor type

F32