Instructions to use Snugasabug/laya-finetuned-rlcd-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Snugasabug/laya-finetuned-rlcd-GGUF 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

llama.cpp

How to use Snugasabug/laya-finetuned-rlcd-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Snugasabug/laya-finetuned-rlcd-GGUF:BF16

Use Docker

docker model run hf.co/Snugasabug/laya-finetuned-rlcd-GGUF:BF16

LM Studio
Jan
Ollama
How to use Snugasabug/laya-finetuned-rlcd-GGUF with Ollama:
```
ollama run hf.co/Snugasabug/laya-finetuned-rlcd-GGUF:BF16
```
Unsloth Desktop
Docker Model Runner
How to use Snugasabug/laya-finetuned-rlcd-GGUF with Docker Model Runner:
```
docker model run hf.co/Snugasabug/laya-finetuned-rlcd-GGUF:BF16
```

Lemonade

How to use Snugasabug/laya-finetuned-rlcd-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Snugasabug/laya-finetuned-rlcd-GGUF:BF16

Run and chat with the model

lemonade run user.laya-finetuned-rlcd-GGUF-BF16

List all available models

lemonade list

Atomic Chat

Laya (Fine-Tuned) — GGUF

GGUF exports of the RLCD fine-tuned laya decision model. Converted from the HF checkpoint at Snugasabug/laya-finetuned-rlcd using the official ggml-org decision-model converter (ggml-org/llama.cpp PR #29818).

Base model: convaiinnovations/laya
HF source checkpoint: Snugasabug/laya-finetuned-rlcd
Encoder: jhu-clsp/mmBERT-base (768-dim), 2 decision-head layers
Architecture: non-autoregressive decision model (ModernBertForMaskedLM encoder + laya decision head)

Files

File	Description
`laya-finetuned-rlcd-bf16.gguf`	Full bf16 weights
`laya-finetuned-rlcd-q8_0.gguf`	Quantized (Q8_0)

Usage

Run with llama.app:

llama serve -hf Snugasabug/laya-finetuned-rlcd-GGUF

This is a decision model served via the /v1/systemone API. Send a state and typed questions (choice / score / noul); the model returns a probability for each option in a single forward pass. See the base model card for the request/response format:

Base model card: https://huggingface.co/convaiinnovations/laya
HF source checkpoint: https://huggingface.co/Snugasabug/laya-finetuned-rlcd

Accuracy claims for the fine-tune are teacher-agreement based (RLCD), evaluated on a 4K subset, and are not measured against human ground truth. See the source checkpoint card for the full caveat.

Downloads last month: 421

GGUF

Model size

0.3B params

Architecture

modern-bert

Hardware compatibility

8-bit

16-bit

Model tree for Snugasabug/laya-finetuned-rlcd-GGUF

Base model

convaiinnovations/laya

Quantized

(85)

this model