Instructions to use rty813/laya-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rty813/laya-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="rty813/laya-bf16")

# pip install -U transformers accelerate
# Load model directly
from transformers import LayaTypedDecisions
model = LayaTypedDecisions.from_pretrained("rty813/laya-bf16", device_map="auto")

Laya

How to use rty813/laya-bf16 with Laya:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rty813/laya-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rty813/laya-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/laya-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rty813/laya-bf16

SGLang

How to use rty813/laya-bf16 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 "rty813/laya-bf16" \
    --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": "rty813/laya-bf16",
		"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 "rty813/laya-bf16" \
        --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": "rty813/laya-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rty813/laya-bf16 with Docker Model Runner:
```
docker model run hf.co/rty813/laya-bf16
```

laya-bf16 (bf16)

Full-precision (bf16) PyTorch port of convaiinnovations/laya, for vLLM / TGI / Xinference / transformers users who don't want the GGUF quant.

Format: pytorch_model.bin (bf16). safetensors conversion in progress.
Architecture: identical to the original — drop-in for AutoModelForCausalLM.from_pretrained("rty813/laya-bf16").
Also loads in vLLM (vllm serve rty813/laya-bf16) and Xinference (search "laya").

Original model card:

license: apache-2.0 library_name: transformers pipeline_tag: text-classification tags: [laya, system-one, calibrated-decisions, rlcd, classification, routing, scoring, guardrails, moderation, reinforcement-learning, commercial-use]

Laya

Multilingual, non-autoregressive System 1 decision model. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with mathematically calibrated probabilities in a single forward pass (~33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (RLCD), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate.

Installation

pip install laya

Python 3.10 or newer. Optional extras: laya[serve] (HTTP server), laya[mcp] (MCP server), laya[langchain] (LangChain and LangGraph), laya[onnx] (ONNX Runtime), laya[fast] (TileLang GPU fast path). Platform-by-platform setup is in the GitHub README.

Long documents. laya-multilingual reads up to 8,192 tokens with max_len=8192. Measured accuracy and time by document length (benchmark script):

Downloads last month: -

Model tree for rty813/laya-bf16

Base model

convaiinnovations/laya

Finetuned

(171)

this model