Index SLM Technical Report

• URL: http://arxiv.org/abs/2607.09885v1
• Date: Fri, 10 Jul 2026 18:19:47 GMT
• Title: Index SLM Technical Report
• Abstract summary: We present Index-1.9B, a series of open small language models developed at Bilibili.<n>The series comprises four models: Index-1.9B-Base, a foundation model with 1.9 billion parameters pre-trained on 2.8 trillion predominantly Chinese and English tokens; Index-1.9B-Pure, a control variant trained with an identical recipe but with all instruction-like data strictly filtered from the corpus; and Index-1.9B-Character, which augments the chat model with retrieval-augmented generation for role-playing customization.
• Score: 11.17580009715777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series comprises four models: Index-1.9B-Base, a foundation model with 1.9 billion non-embedding parameters pre-trained on 2.8 trillion predominantly Chinese and English tokens; Index-1.9B-Pure, a control variant trained with an identical recipe but with all instruction-like data strictly filtered from the corpus; Index-1.9B-Chat, aligned from the base model with supervised fine-tuning and direct preference optimization; and Index-1.9B-Character, which augments the chat model with retrieval-augmented generation for few-shot role-playing customization. Pre-training employs a Warmup-Stable-Decay learning-rate schedule in which the concentration of curated data is raised substantially during the decay phase, together with a Norm-Head output layer that stabilizes training under large learning rates. On a suite of standard benchmarks covering examination, reasoning, mathematics, and code, Index-1.9B-Base attains an average score of 64.92, competitive with or exceeding open models of several times its size. We further report controlled studies on model depth, learning-rate magnitude and scheduling, the interaction between learning-rate decay and data quality, and the effect of including instruction data during pre-training, and we document an unexplained surge in benchmark performance midway through the constant-learning-rate phase. All models, together with evaluation code, are released at https://github.com/bilibili/Index-1.9B.

Related papers

• TabH2O: A Unified Foundation Model for Tabular Prediction [12.882141870947706]
  We present TabH2O, a model that performs classification and regression in a single forward pass via in-context learning.<n>We evaluate TabH2O v1 (29.2M parameters) on the TALENT benchmark, where it achieves an average rank of 2.55 out of 6 evaluated methods.
  arXiv  Detail & Related papers  (2026-05-18T13:27:54Z)
• How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining [22.50461083222824]
  A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on data sorted in ascending order of quality as determined by a quality metric.<n>This work identifies a critical factor constraining these methods: the incompatibility between the ascending data quality order and the decaying learning rate schedule.
  arXiv  Detail & Related papers  (2025-11-24T09:03:49Z)
• Approximating Language Model Training Data from Weights [70.08614275061689]
  We formalize the problem of data approximation from model weights and propose several baselines and metrics.<n>We develop a gradient-based approach that selects the highest-matching data from a large public text corpus.<n>Even when none of the true training data is known, our method is able to locate a small subset of public Web documents.
  arXiv  Detail & Related papers  (2025-06-18T15:26:43Z)
• Pretraining Language Models to Ponder in Continuous Space [50.52734567589996]
  We introduce this pondering process into language models by repeatedly invoking the forward process within a single token generation step.<n>We show that the model can learn to ponder in this way through self-supervised learning, without any human annotations.
  arXiv  Detail & Related papers  (2025-05-27T03:47:33Z)
• WorldPM: Scaling Human Preference Modeling [130.23230492612214]
  We propose World Preference Modeling$ (WorldPM) to emphasize this scaling potential.<n>We collect preference data from public forums covering diverse user communities.<n>We conduct extensive training using 15M-scale data across models ranging from 1.5B to 72B parameters.
  arXiv  Detail & Related papers  (2025-05-15T17:38:37Z)
• Privacy-Preserved Automated Scoring using Federated Learning for Educational Research [1.2556373621040728]
  We propose a federated learning (FL) framework for automated scoring of educational assessments.<n>We benchmark our model against two state-of-the-art FL methods and a centralized learning baseline.<n>Results show that our model achieves the highest accuracy (94.5%) among FL approaches.
  arXiv  Detail & Related papers  (2025-03-12T19:06:25Z)
• Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data [39.40116554523575]
  We present Drift-Resilient TabPFN, a fresh approach based on In-Context Learning with a Prior-Data Fitted Network. It learns to approximate Bayesian inference on synthetic datasets drawn from a prior. It improves accuracy from 0.688 to 0.744 and ROC AUC from 0.786 to 0.832 while maintaining stronger calibration.
  arXiv  Detail & Related papers  (2024-11-15T23:49:23Z)
• Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models [75.9543301303586]
  Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that prior work has overlooked the inherent biases in foundation models.
  arXiv  Detail & Related papers  (2023-10-12T08:01:11Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.