REVIEW 7 cited by
LLaMA Pro: Progressive LLaMA with Block Expansion
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
read the original abstract
Humans generally acquire new skills without compromising the old; however, the opposite holds for Large Language Models (LLMs), e.g., from LLaMA to CodeLLaMA. To this end, we propose a new post-pretraining method for LLMs with an expansion of Transformer blocks. We tune the expanded blocks using only new corpus, efficiently and effectively improving the model's knowledge without catastrophic forgetting. In this paper, we experiment on the corpus of code and math, yielding LLaMA Pro-8.3B, a versatile foundation model initialized from LLaMA2-7B, excelling in general tasks, programming, and mathematics. LLaMA Pro and its instruction-following counterpart (LLaMA Pro-Instruct) achieve advanced performance among various benchmarks, demonstrating superiority over existing open models in the LLaMA family and the immense potential of reasoning and addressing diverse tasks as an intelligent agent. Our findings provide valuable insights into integrating natural and programming languages, laying a solid foundation for developing advanced language agents that operate effectively in various environments.
Forward citations
Cited by 7 Pith papers
-
Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio
Trained connectors and audio-only gated adapters integrate audio into a frozen vision-language embedding space, preserving base outputs bit-exactly and yielding emergent audio-image retrieval.
-
Scaling depth capacity via zero/one-layer model expansion
Training GPT2 from a zero/one-layer model and expanding depth at 80% of the schedule reaches fixed-size loss with approximately 5x less compute.
-
Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian
Llama-GENBA-10B is a 10B-parameter trilingual model that reports top Bavarian scores among sub-10B models on a machine-translated benchmark the authors built.
-
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
A LoRA update split into several fixed, differently-scaled low-rank experts with orthogonal input directions improves fine-tuning accuracy at the same parameter count.
-
Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study
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.
-
Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
CorDA++ uses data-driven SVD to initialize LoRA adapters, adding per-layer covariance selection and rank allocation that reduce forgetting and speed convergence compared to LoRA, PiSSA, QLoRA, and other baselines.
-
Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts
A layer-wise expert allocation algorithm based on hidden-state similarity, plus a routing classifier, improves parameter efficiency and reduces forgetting when expanding LLMs to new languages.
Discussion (0). Sign in to comment.