Triangle104/Llama3-Crab-DPO-Q4_K_S-GGUF

This model was converted to GGUF format from THU-KEG/Llama3-Crab-DPO using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

---

Model details:

Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc. Following the conventional instruction-tuning practice, previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs. However, even advanced LLMs cannot follow complex instructions well, thus limiting the quality of generated data. In this work, we find that existing datasets inherently contain implicit complex constraints and propose a novel data generation technique, constraint back-translation. Specifically, we take the high-quality instruction-response pairs in existing datasets and only adopt advanced LLMs to add complex constraints already met by the responses to the instructions, which naturally reduces costs and data noise. In the experiments, we adopt Llama3-70B-Instruct to back-translate constraints and create a high-quality complex instruction-response dataset, named CRAB. We present that post-training on CRAB improves multiple backbone LLMs' complex instruction-following ability, evaluated on extensive instruction-following benchmarks. We further find that constraint back-translation also serves as a useful auxiliary training objective in post-training.

📖 Paper: Constraint Back-translation Improves Complex Instruction Following of Large Language Models

🦀 Github: THU/Crab

Model Description

Developed by: Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li
Model type: Text Generation
Language(s) (NLP): English
Finetuned from model [optional]: Llama3-8B

---

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Triangle104/Llama3-Crab-DPO-Q4_K_S-GGUF --hf-file llama3-crab-dpo-q4_k_s.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Llama3-Crab-DPO-Q4_K_S-GGUF --hf-file llama3-crab-dpo-q4_k_s.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo Triangle104/Llama3-Crab-DPO-Q4_K_S-GGUF --hf-file llama3-crab-dpo-q4_k_s.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Triangle104/Llama3-Crab-DPO-Q4_K_S-GGUF --hf-file llama3-crab-dpo-q4_k_s.gguf -c 2048