---

license: llama3

base_model: meta-llama/Meta-Llama-3-8B

library_name: llama.cpp

pipeline_tag: text-generation

tags:

- gguf

- rest-api-testing

- software-testing

- llama.cpp

- llamaresttest

language:

- en

---

LlamaREST-EX (GGUF)

LlamaREST-EX is a Small Language Model (SLM) fine-tuned to generate realistic

example values for REST API parameters, used by

LlamaRestTest to improve automated

REST API test generation.

It is one of the two SLMs used by LlamaRestTest; the companion model,

LlamaREST-IPD, predicts

inter-parameter dependencies.

Models

Quantized with llama.cpp (Q6_K) from a Llama-3-8B base fine-tuned with QLoRA.

| Variant | File | Size |

|---|---|---|

| 2B | LlamaREST-EX-2B.gguf | ~3.2 GB |

| 4B | LlamaREST-EX-4B.gguf | ~4.9 GB |

| 8B | LlamaREST-EX-8B.gguf | ~8.5 GB |

| F16 | Llama3-Ex-Rest-8.0B-F16.gguf | ~1.3 GB |

Download

pip install -U "huggingface_hub[cli]"
hf download codingsoo/LlamaREST-EX-GGUF LlamaREST-EX-8B.gguf --local-dir .

Usage

Intended to be run through the LlamaRestTest

pipeline. To run the GGUF directly with llama.cpp:

./llama-cli -m LlamaREST-EX-8B.gguf -p "your prompt"

Training

Fine-tuned from Llama-3-8B with QLoRA, then quantized with llama.cpp (Q6_K). Key hyperparameters:

• 4-bit precision (nf4), compute dtype float16, no nested quantization
• LoRA: r=64, alpha=16, dropout 0.1
• 5 epochs, batch size 4, paged_adamw_32bit, LR 2e-4, weight decay 0.001, constant schedule, warmup ratio 0.03

Training data (Examples): random1234321/REST-EX.

License

The training/testing code is released under the MIT License. The model weights are

derived from Meta Llama 3 and are therefore subject to the

Meta Llama 3 Community License.

Citation

@article{kim2025llamaresttest,
  title={LlamaRestTest: Effective REST API Testing with Small Language Models},
  author={Kim, Myeongsoo and Sinha, Saurabh and Orso, Alessandro},
  journal={arXiv preprint arXiv:2501.08598},
  year={2025}
}