Pith. sign in

REVIEW 16 cited by

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.15166 v3 pith:4HSQ7NMH submitted 2023-12-23 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords scalingsolarlanguagellmsup-scalingdeptheffectiveefficiently
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce SOLAR 10.7B, a large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. Inspired by recent efforts to efficiently up-scale LLMs, we present a method for scaling LLMs called depth up-scaling (DUS), which encompasses depthwise scaling and continued pretraining. In contrast to other LLM up-scaling methods that use mixture-of-experts, DUS does not require complex changes to train and inference efficiently. We show experimentally that DUS is simple yet effective in scaling up high-performance LLMs from small ones. Building on the DUS model, we additionally present SOLAR 10.7B-Instruct, a variant fine-tuned for instruction-following capabilities, surpassing Mixtral-8x7B-Instruct. SOLAR 10.7B is publicly available under the Apache 2.0 license, promoting broad access and application in the LLM field.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Chain-of-Experts replaces one parallel MoE routing step with several sequential expert steps inside a layer, reporting lower loss and memory use in small-scale experiments.

  2. Resilient LLM-Empowered Semantic MAC Protocols via Zero-Shot Adaptation and Knowledge Distillation

    cs.NI 2025-05 conditional novelty 6.0 of 10

    A hybrid MAC protocol that starts with LLM-generated control messages and switches to a distilled neural model after retraining improves resilience to user-count changes at lower compute than pure LLM inference.

  3. Latent Flow Transformer

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LFT replaces up to 13 of 24 transformer layers of Pythia-410M with a single flow-based layer trained with Flow Walking, achieving KL 0.736 vs 0.932 for skipping three layers.

  4. Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging

    cs.AI 2025-02 conditional novelty 6.0 of 10

    An automated multi-fidelity search framework discovers layer-wise and depth-wise model merging recipes that improve single- and multi-objective LLM reasoning performance without retraining.

  5. Unraveling the Capabilities of Language Models in News Summarization

    cs.CL 2025-01 conditional novelty 6.0 of 10

    A 20-model benchmark on three news datasets finds GPT-3.5/GPT-4 lead, a few small models are competitive, and three-shot demonstrations with low-quality gold summaries fail to help.

  6. Channel Merging: Preserving Specialization for Merged Experts

    cs.CL 2024-12 conditional novelty 6.0 of 10

    Channel Merging clusters similar channel parameters from fine-tuned LLMs and reconstructs the selected expert at inference, matching unmerged accuracy with about 53% of the ensemble's parameters.

  7. Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A new fine-grained benchmark and an observation-and-memory chain-of-thought fine-tuning method for simulating social media user behavior.

  8. CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield

    cs.CL 2026-06 unverdicted novelty 5.0 of 10

    Selective-pivot-token training plus layer-averaging-with-recurrence reportedly gives 2.5x parameter compression on a small Korean LLM, but the efficiency claim lacks its decisive controls and the abstract advertises r...

  9. Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A 102B Korean-English model, expanded from Llama 3 70B with LlamaPro and Masked Structure Growth and trained on 194B tokens, scores 64.74 on KMMLU and 83.34 on KorMedMCQA, roughly matching GPT-4 on Korean benchmarks.

  10. An Empirical Study of Evaluating Long-form Question Answering

    cs.IR 2025-04 conditional novelty 5.0 of 10

    In long-form QA, LLM-based evaluators correlate with human judgments better than ROUGE or BERTScore, but they are biased by answer length, question type, self-reinforcement, and rare-word usage, and fine-grained promp...

  11. Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

    cs.CL 2025-02 conditional novelty 5.0 of 10

    CoSD fuses two LLMs at decoding time: it keeps the draft model's tokens unless a confidence rule or a decision tree over token probabilities says the assistant model's token is better.

  12. Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field

    cs.DL 2024-12 conditional novelty 5.0 of 10

    Zero-shot LLMs, especially Claude 3 Sonnet and a fine-tuned 7B Mistral variant, classify semantic relations between engineering research topics with high F1 on the new IEEE-Rel-1K benchmark.

  13. ResidualDroppath: Enhancing Feature Reuse over Residual Connections

    cs.LG 2024-11 conditional novelty 5.0 of 10

    A two-phase training algorithm alternating droppath steps with frozen-path steps gives modest accuracy improvements on small image datasets, with inconsistent ImageNet results.

  14. SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought

    cs.AI 2025-05 conditional novelty 4.0 of 10

    SCOUT combines progressive distillation with a cross-attention module to make recursive latent reasoning work through fine-tuning, yielding up to 1.8% accuracy gains over standard fine-tuning.

  15. Efficient Speech Translation through Model Compression and Knowledge Distillation

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Iterative decoder pruning plus QLoRA and knowledge distillation compress Qwen2-Audio-7B by up to 50% with 97-100% of teacher translation quality on English-German and English-Chinese.

  16. DNA 1.0 Technical Report

    cs.CL 2025-01 conditional novelty 4.0 of 10

    DNA 1.0 8B Instruct is an 8-billion-parameter Korean-English model that reports state-of-the-art results on Korean benchmarks through continual pre-training, SLERP merging, DPO, and distillation.

Pith tools