AmberSafe

We present AmberSafe, a safety-finetuned instruction model using LLM360/AmberChat as the base. AmberSafe is part of LLM360's Pebble model series.

Model Description

Model type: Language model with the same architecture as LLaMA-7B
Language(s) (NLP): English
License: Apache 2.0
Resources for more information:
Metrics
Fully processed Amber pretraining data
Finetuning Code

Loading AmberSafe

import torch
from transformers import LlamaTokenizer, LlamaForCausalLM

tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberSafe")
model = LlamaForCausalLM.from_pretrained("LLM360/AmberSafe")

#template adapated from fastchat
template= "###Human: {prompt}\n###Assistant:"

prompt = "How do I mount a tv to drywall safely?"

input_str = template.format(prompt=prompt)
input_ids = tokenizer(input_str, return_tensors="pt").input_ids
outputs = model.generate(input_ids, max_length=1000)
print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())

Alternatively, you may use FastChat:

python3 -m fastchat.serve.cli --model-path LLM360/AmberSafe

AmberSafe Finetuning Details

DataMix

| Subset | Number of rows | License |

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

| PKU-Alignment/PKU-SafeRLHF | 330k | cc-by-nc-4.0 |

| Total | 330k | |

Data Preprocessing

We filtered the dataset by selecting all data samples with different boolean values in is_response_0_safe and is_response_1_safe. This would make sure that for each pair in the preference dataset, the chosen text is safe and the rejected one is unsafe.

Method

We followed the instructions in the dpo repo to finetune this model.

1. Run supervised fine-tuning (SFT) on the dataset(s) of interest.

2. Run preference learning on the model from step 1, using preference data (ideally from the same distribution as the SFT examples).

Evaluation

| Model | MT-Bench |

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

| LLM360/Amber 359 | 2.48750 |

| LLM360/AmberChat | 5.428125 |

| LLM360/AmberSafe | 4.725000 |

Using Quantized Models with Ollama

Please follow these steps to use a quantized version of AmberSafe on your personal computer or laptop:

1. First, install Ollama by following the instructions provided here. Next, create a quantized version of AmberSafe model (say ambersafe.Q8_0.gguf for 8 bit quantized version) following instructions here. Alternatively, you can download the 8bit quantized version that we created ambersafe.Q8_0.gguf

2. Create an Ollama Modelfile locally using the template provided below:

FROM ambersafe.Q8_0.gguf

TEMPLATE """{{ .System }}
USER: {{ .Prompt }}
ASSISTANT:
"""
SYSTEM """A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
"""
PARAMETER stop "USER:"
PARAMETER stop "ASSISTANT:"
PARAMETER repeat_last_n   0
PARAMETER num_ctx         2048
PARAMETER seed            0
PARAMETER num_predict    -1

Ensure that the FROM directive points to the created checkpoint file.

3. Now, you can proceed to build the model by running:

ollama create ambersafe -f Modelfile

4. To run the model from the command line, execute the following:

ollama run ambersafe

You need to build the model once and can just run it afterwards.

Citation

BibTeX:

@misc{liu2023llm360,
      title={LLM360: Towards Fully Transparent Open-Source LLMs}, 
      author={Zhengzhong Liu and Aurick Qiao and Willie Neiswanger and Hongyi Wang and Bowen Tan and Tianhua Tao and Junbo Li and Yuqi Wang and Suqi Sun and Omkar Pangarkar and Richard Fan and Yi Gu and Victor Miller and Yonghao Zhuang and Guowei He and Haonan Li and Fajri Koto and Liping Tang and Nikhil Ranjan and Zhiqiang Shen and Xuguang Ren and Roberto Iriondo and Cun Mu and Zhiting Hu and Mark Schulze and Preslav Nakov and Tim Baldwin and Eric P. Xing},
      year={2023},
      eprint={2312.06550},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

IFM/AmberSafe