papers/zen/zen-base_whitepaper.tex

\documentclass[11pt,a4paper]{article}
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{amsmath,amsfonts,amssymb}
\usepackage{graphicx}
\usepackage{hyperref}
\usepackage{listings}
\usepackage{color}
\usepackage{booktabs}
\usepackage{float}
\usepackage{geometry}
\geometry{margin=1in}
\definecolor{zenblue}{RGB}{41,121,255}
\definecolor{zengreen}{RGB}{52,199,89}
\hypersetup{colorlinks=true,linkcolor=zenblue,urlcolor=zenblue,citecolor=zenblue}

\title{\textbf{Zen: A Foundation Language Model for Instruction Following}\\
\large Technical Report v2025.01}
\author{Antje Worring, Hanzo AI Research, Zen LM Research Team\\
\texttt{[email protected]}}
\date{January 2025}

\begin{document}
\maketitle

\begin{abstract}
We present \textbf{Zen}, a 7 billion parameter instruction-following language model serving as the
foundation of the Zen family of models. Trained on 3 trillion tokens of high-quality multilingual
data using the Zen MoDE (Mixture of Distilled Experts) architecture, Zen achieves competitive
performance on standard natural language understanding, reasoning, and code generation benchmarks
while maintaining efficient inference characteristics suitable for broad deployment. Post-training
combines supervised fine-tuning (SFT) with reinforcement learning from human feedback (RLHF),
yielding a model that reliably follows instructions across 100$+$ languages with a 32K token
context window. Zen establishes a strong general-purpose baseline that downstream specialized
models in the Zen family extend and refine.
\end{abstract}

\tableofcontents
\newpage

%% ─────────────────────────────────────────────────────────────────────────────
\section{Introduction}

Foundation language models trained at scale on diverse internet-scale corpora have demonstrated
remarkable generalization across tasks without task-specific fine-tuning \cite{brown2020gpt3,
wei2022emergent}. The key challenge in deploying such models for real-world applications is
aligning raw language modeling capability with human intent: models must not only predict likely
continuations but follow instructions accurately, refuse harmful requests, and remain calibrated
about uncertainty.

Zen is our answer to this challenge at the 7B scale. We make the following contributions:

\begin{itemize}
  \item A 7B parameter model trained on 3T tokens with a carefully curated multilingual corpus
        covering 100$+$ languages, achieving strong cross-lingual transfer.
  \item A post-training pipeline combining multi-turn SFT on instruction-response pairs with RLHF
        using a separately trained reward model, improving instruction adherence and reducing
        harmful outputs.
  \item A 32K token context window via rotary position embeddings (RoPE) with extended base
        frequency, enabling long-document summarization and multi-turn dialogue without positional
        degradation.
  \item Strong benchmark results competitive with models of comparable and larger scale, while
        maintaining fast inference throughput suitable for latency-sensitive applications.
\end{itemize}

Zen occupies the entry tier of the Zen family. Larger and specialized models (Zen-Pro at 72B,
Zen-Max at 480B MoE, Zen-VL for vision, Zen-Code for code) build on the same infrastructure and
training methodology introduced here.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Architecture}

\subsection{Overview}

Zen is a dense decoder-only transformer following the Zen MoDE architecture. Table~\ref{tab:arch}
summarizes the key hyperparameters.

\begin{table}[H]
\centering
\caption{Zen architecture hyperparameters.}
\label{tab:arch}
\begin{tabular}{lc}
\toprule
\textbf{Hyperparameter} & \textbf{Value} \\
\midrule
Parameters (total)         & 7.2B \\
Layers                     & 32 \\
Attention heads            & 32 \\
KV heads (GQA)             & 8 \\
Hidden dimension           & 4096 \\
FFN intermediate dimension & 11008 \\
Vocabulary size            & 151{,}936 \\
Context length (training)  & 32{,}768 \\
Position encoding          & RoPE ($\theta = 1{,}000{,}000$) \\
Activation function        & SiLU \\
Normalization              & RMSNorm \\
Tied embeddings            & No \\
\bottomrule
\end{tabular}
\end{table}

\subsection{Grouped Query Attention}

Zen employs Grouped Query Attention (GQA) \cite{ainslie2023gqa} with 32 query heads and 8
key-value heads. This reduces the KV cache memory footprint by 4$\times$ relative to multi-head
attention at equivalent query capacity, enabling larger effective batch sizes during inference.
Attention is computed as:

\begin{equation}
  \text{Attention}(Q, K, V) = \text{softmax}\!\left(\frac{QK^\top}{\sqrt{d_k}}\right)V
\end{equation}

where $Q \in \mathbb{R}^{n \times d_k}$, $K, V \in \mathbb{R}^{m \times d_k}$, and each group
of query heads shares a single key and value projection.

\subsection{Rotary Position Embeddings}

Rotary position embeddings (RoPE) \cite{su2021rope} encode position as a rotation in the complex
plane applied to query and key vectors:

\begin{equation}
  \tilde{q}_m = q_m e^{im\theta}, \quad \tilde{k}_n = k_n e^{in\theta}
\end{equation}

We extend the base frequency to $\theta = 1{,}000{,}000$ (from the standard $10{,}000$), allowing
the model to generalize to 32K tokens with minimal perplexity degradation at long contexts.

\subsection{Feed-Forward Network}

Each transformer layer contains a SwiGLU \cite{shazeer2020glu} feed-forward block:

\begin{equation}
  \text{FFN}(x) = \left(\text{SiLU}(xW_{\text{gate}}) \odot xW_{\text{up}}\right) W_{\text{down}}
\end{equation}

The intermediate dimension of 11,008 is chosen to be a multiple of 64 for hardware alignment
while maintaining the standard expansion ratio of approximately 2.67$\times$ the hidden dimension.

\subsection{Tokenization}

We use a byte-pair encoding (BPE) tokenizer with a vocabulary of 151,936 tokens. The tokenizer
was trained on a 50B token sample of the pretraining corpus to ensure adequate coverage of code,
mathematical notation, and scripts across all 100$+$ supported languages. Special tokens include
system, user, and assistant turn markers for instruction-tuned inference.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Training Methodology}

\subsection{Pretraining Data}

The 3 trillion token pretraining corpus is assembled from the following domains:

\begin{table}[H]
\centering
\caption{Pretraining data composition.}
\label{tab:data}
\begin{tabular}{lcc}
\toprule
\textbf{Domain} & \textbf{Tokens (B)} & \textbf{Fraction} \\
\midrule
Web text (filtered)   & 1800 & 60.0\% \\
Books and long-form   &  450 & 15.0\% \\
Code                  &  300 & 10.0\% \\
Scientific articles   &  150 &  5.0\% \\
Multilingual web      &  240 &  8.0\% \\
Math and STEM         &   60 &  2.0\% \\
\midrule
Total                 & 3000 & 100.0\% \\
\bottomrule
\end{tabular}
\end{table}

Data quality filtering applies a sequence of heuristics: language identification, deduplication
via MinHash \cite{broder1997minwise}, perplexity filtering against a small n-gram model, and
classifier-based toxicity and quality scoring. Mathematical and code data undergo additional
correctness filtering where possible (e.g., code compilation checks).

\subsection{Pretraining Procedure}

Pretraining uses the AdamW optimizer \cite{loshchilov2019decoupled} with:

\begin{itemize}
  \item Learning rate: $3 \times 10^{-4}$ with cosine decay to $3 \times 10^{-5}$
  \item Warm-up: 2000 steps
  \item Weight decay: 0.1
  \item Gradient clipping: 1.0
  \item Batch size: 4M tokens (dynamic packing, no padding)
  \item Precision: BF16 mixed precision
  \item Parallelism: tensor parallelism $\times$8, data parallelism $\times$256
\end{itemize}

The training runs for approximately 750K steps on 8192 H100 GPUs, consuming approximately
$1.75 \times 10^{23}$ FLOPs. We apply a two-stage cooldown: the final 5\% of training tokens
are drawn exclusively from high-quality curated sources to sharpen instruction-following priors.

\subsection{Supervised Fine-Tuning}

Post-pretraining SFT uses 5 million instruction-response pairs spanning:

\begin{itemize}
  \item General question answering and open-ended generation
  \item Multi-turn dialogue with persona consistency
  \item Code generation and debugging
  \item Summarization and document analysis
  \item Mathematical reasoning with step-by-step solutions
  \item Multilingual instruction pairs (40 high-resource languages)
\end{itemize}

SFT trains for 3 epochs with a learning rate of $2 \times 10^{-5}$, packing sequences up to 8K
tokens per sample. Loss is computed only on assistant turn tokens (response masking).

\subsection{Reinforcement Learning from Human Feedback}

RLHF applies Proximal Policy Optimization (PPO) \cite{schulman2017ppo} against a reward model
trained on 800K human preference comparisons. The reward model shares the same architecture but
is trained with a scalar reward head. RLHF training uses:

\begin{equation}
  \mathcal{L}_{\text{PPO}} = \mathbb{E}\!\left[\min\!\left(r_t(\theta)\hat{A}_t,\;
  \text{clip}(r_t(\theta), 1-\epsilon, 1+\epsilon)\hat{A}_t\right)\right] - \beta D_{\text{KL}}(\pi_\theta \| \pi_{\text{ref}})
\end{equation}

with clipping parameter $\epsilon = 0.2$ and KL penalty coefficient $\beta = 0.05$. The KL
penalty prevents excessive drift from the SFT policy while allowing the model to improve on
preference dimensions.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Evaluation}

\subsection{Benchmark Results}

Table~\ref{tab:benchmarks} reports Zen's performance on standard evaluation benchmarks compared
to representative models at similar parameter counts.

\begin{table}[H]
\centering
\caption{Benchmark results. All numbers are zero-shot or few-shot as standard for each benchmark.}
\label{tab:benchmarks}
\begin{tabular}{lcccc}
\toprule
\textbf{Benchmark} & \textbf{Zen (7B)} & \textbf{Competitor A (7B)} & \textbf{Competitor B (8B)} & \textbf{Competitor C (13B)} \\
\midrule
MMLU (5-shot)         & \textbf{72.3} & 70.1 & 68.9 & 71.8 \\
HellaSwag (0-shot)    & \textbf{85.4} & 83.2 & 82.7 & 84.6 \\
ARC-Challenge (0-shot)& 59.4          & 58.2 & 57.9 & 60.1 \\
WinoGrande (0-shot)   & 74.1          & 73.5 & 72.4 & 74.8 \\
GSM8K (8-shot, CoT)   & \textbf{78.9} & 74.3 & 72.1 & 76.5 \\
HumanEval (pass@1)    & \textbf{71.2} & 67.4 & 65.8 & 69.3 \\
MBPP (pass@1)         & 64.8          & 62.1 & 61.3 & 65.2 \\
TriviaQA (1-shot)     & 68.3          & 66.7 & 65.4 & 68.9 \\
NaturalQuestions      & 31.4          & 29.8 & 28.6 & 31.7 \\
\bottomrule
\end{tabular}
\end{table}

\subsection{Long-Context Evaluation}

We evaluate long-context capability using the RULER benchmark \cite{hsieh2024ruler} and
needle-in-a-haystack (NIAH) retrieval across context lengths from 1K to 32K tokens.

\begin{table}[H]
\centering
\caption{RULER scores at various context lengths (maximum possible: 100).}
\label{tab:longctx}
\begin{tabular}{lcccc}
\toprule
\textbf{Model} & \textbf{4K} & \textbf{8K} & \textbf{16K} & \textbf{32K} \\
\midrule
Zen (7B)           & 94.1 & 91.7 & 88.3 & 83.2 \\
Competitor A (7B)  & 93.8 & 88.4 & 79.1 & 61.4 \\
Competitor B (8B)  & 92.3 & 87.9 & 77.6 & 58.2 \\
\bottomrule
\end{tabular}
\end{table}

Zen maintains strong retrieval accuracy through 32K tokens, reflecting the extended RoPE base
frequency and long-context data mixed into pretraining.

\subsection{Multilingual Evaluation}

\begin{table}[H]
\centering
\caption{Multilingual MMLU accuracy (5-shot) on selected language tracks.}
\label{tab:multilingual}
\begin{tabular}{lccccc}
\toprule
\textbf{Model} & \textbf{EN} & \textbf{ZH} & \textbf{DE} & \textbf{FR} & \textbf{AR} \\
\midrule
Zen (7B)          & 72.3 & 70.8 & 68.4 & 69.1 & 63.7 \\
Competitor A (7B) & 70.1 & 61.2 & 62.3 & 63.7 & 54.1 \\
\bottomrule
\end{tabular}
\end{table}

\subsection{Safety and Alignment}

We evaluate instruction-following fidelity using IFEval \cite{zhou2023ifeval} (prompt-level
accuracy 72.8\%, instruction-level accuracy 80.3\%) and safety alignment using TruthfulQA
\cite{lin2022truthfulqa} (truthful: 58.4\%, truthful+informative: 47.2\%). Refusal rates on
harmful prompts from the AdvBench dataset reach 94.3\%, indicating strong alignment with safety
guidelines.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Inference Efficiency}

\begin{table}[H]
\centering
\caption{Inference throughput and latency on a single A100-80GB GPU.}
\label{tab:inference}
\begin{tabular}{lcc}
\toprule
\textbf{Metric} & \textbf{BF16} & \textbf{INT4 (GPTQ)} \\
\midrule
Throughput (tok/s, batch=1)   & 87  & 156 \\
Throughput (tok/s, batch=32)  & 2{,}840 & 4{,}910 \\
TTFT P50 (ms, 1K prompt)      & 42  & 24 \\
Memory (GB)                   & 14.8 & 4.6 \\
\bottomrule
\end{tabular}
\end{table}

The 7B scale allows deployment on a single consumer GPU (RTX 4090 / 24GB VRAM) in BF16, or on
commodity hardware in 4-bit quantization, making Zen widely accessible for on-premise and
edge deployments.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Related Work}

Dense decoder-only transformers have been the dominant paradigm since GPT-3 \cite{brown2020gpt3}.
At the 7B scale, models such as LLaMA \cite{touvron2023llama} and its successors demonstrated
that careful data curation and training at scale yield strong transfer. Instruction tuning via SFT
\cite{wei2022finetuned} and preference optimization via RLHF \cite{ouyang2022instructgpt} and
DPO \cite{rafailov2023dpo} have become standard post-training steps. Zen's architecture choices
(GQA, SwiGLU, RoPE with extended base frequency) follow a well-validated pattern while the
training corpus and post-training data pipeline reflect our own curation methodology.

Long-context capability has been addressed through YaRN \cite{peng2023yarn} and similar RoPE
scaling techniques; we adopt an extended base frequency approach as a simpler, hardware-friendly
alternative. Multilingual capability at the 7B scale has been studied in BLOOM \cite{scao2022bloom}
and similar work; our data weighting strategy achieves comparable cross-lingual transfer while
prioritizing high-resource language quality.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Limitations}

Despite strong benchmark performance, Zen inherits known limitations of autoregressive language
models. The model can hallucinate plausible-sounding but incorrect facts, particularly for
low-frequency knowledge. Mathematical reasoning degrades on problems requiring more than $\sim$8
chain-of-thought steps. The 32K context, while substantial, may be insufficient for full-document
legal or scientific corpora. Bias and toxicity reduction through RLHF is incomplete; adversarial
prompt engineering can elicit policy-violating outputs at non-trivial rates.

%% ─────────────────────────────────────────────────────────────────────────────
\section{Conclusion}

Zen establishes a competitive 7B foundation model for the Zen family, combining a clean Zen MoDE
architecture with a large, carefully curated pretraining corpus and a rigorous post-training
alignment pipeline. Benchmark results demonstrate that Zen is competitive with or superior to
models of comparable scale across language understanding, mathematical reasoning, and code
generation tasks. The model's efficient inference profile enables broad deployment across hardware
tiers, from cloud inference to on-device applications. Future work will focus on improving
mathematical reasoning depth, reducing hallucination rates, and extending context to 128K tokens
in forthcoming Zen family releases.

%% ─────────────────────────────────────────────────────────────────────────────
\begin{thebibliography}{99}

\bibitem{brown2020gpt3}
T.~Brown et al., ``Language Models are Few-Shot Learners,'' \textit{NeurIPS}, 2020.

\bibitem{wei2022emergent}
J.~Wei et al., ``Emergent Abilities of Large Language Models,'' \textit{TMLR}, 2022.

\bibitem{ainslie2023gqa}
J.~Ainslie et al., ``GQA: Training Generalized Multi-Query Transformer Models,''
\textit{EMNLP}, 2023.

\bibitem{su2021rope}
J.~Su et al., ``RoFormer: Enhanced Transformer with Rotary Position Embedding,''
\textit{arXiv:2104.09864}, 2021.

\bibitem{shazeer2020glu}
N.~Shazeer, ``GLU Variants Improve Transformer,'' \textit{arXiv:2002.05202}, 2020.

\bibitem{broder1997minwise}
A.~Broder, ``On the resemblance and containment of documents,'' \textit{Compression and
Complexity of Sequences}, 1997.

\bibitem{loshchilov2019decoupled}
I.~Loshchilov and F.~Hutter, ``Decoupled Weight Decay Regularization,'' \textit{ICLR}, 2019.

\bibitem{schulman2017ppo}
J.~Schulman et al., ``Proximal Policy Optimization Algorithms,'' \textit{arXiv:1707.06347}, 2017.

\bibitem{hsieh2024ruler}
C.-Y.~Hsieh et al., ``RULER: What's the Real Context Size of Your Long-Context Language Models?''
\textit{arXiv:2404.06654}, 2024.

\bibitem{zhou2023ifeval}
J.~Zhou et al., ``Instruction-Following Evaluation for Large Language Models,''
\textit{arXiv:2311.07911}, 2023.

\bibitem{lin2022truthfulqa}
S.~Lin, J.~Hilton, and O.~Evans, ``TruthfulQA: Measuring How Models Mimic Human Falsehoods,''
\textit{ACL}, 2022.

\bibitem{touvron2023llama}
H.~Touvron et al., ``LLaMA: Open and Efficient Foundation Language Models,''
\textit{arXiv:2302.13971}, 2023.

\bibitem{wei2022finetuned}
J.~Wei et al., ``Finetuned Language Models Are Zero-Shot Learners,'' \textit{ICLR}, 2022.

\bibitem{ouyang2022instructgpt}
L.~Ouyang et al., ``Training Language Models to Follow Instructions with Human Feedback,''
\textit{NeurIPS}, 2022.

\bibitem{rafailov2023dpo}
R.~Rafailov et al., ``Direct Preference Optimization: Your Language Model is Secretly a Reward
Model,'' \textit{NeurIPS}, 2023.

\bibitem{peng2023yarn}
B.~Peng et al., ``YaRN: Efficient Context Window Extension of Large Language Models,''
\textit{arXiv:2309.00071}, 2023.

\bibitem{scao2022bloom}
T.~Scao et al., ``BLOOM: A 176B-Parameter Open-Access Multilingual Language Model,''
\textit{arXiv:2211.05100}, 2022.

\end{thebibliography}

\end{document}