·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
US threatens sanctions against Chinese AI models over IP theft52m◆Google launches a cheaper alternative to large AI security models like Mythos1h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated3h◆Halliday’s latest smart glasses feature a much-improved display3h◆America needs to stop getting shocked by Chinese AI5h◆Advancing next-gen AI with materials science innovation5h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else6h◆Capacity and Redundancy Trade-offs in Multi-Task Learning12h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation12h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making12h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection12h◆Supervised Reward Inference12h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization12h◆Is Progressive Disclosure All You Need for Long-Context Agents?12h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability12h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification12h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration12h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI12h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models12h◆AI-Augmented Human Resource Management? Insights from German companies12h◆US threatens sanctions against Chinese AI models over IP theft52m◆Google launches a cheaper alternative to large AI security models like Mythos1h◆Music streamer Deezer says more than 50% of daily uploads are AI-generated3h◆Halliday’s latest smart glasses feature a much-improved display3h◆America needs to stop getting shocked by Chinese AI5h◆Advancing next-gen AI with materials science innovation5h◆Gritt exits stealth with $32 million for robots to build solar plants — then, everything else6h◆Capacity and Redundancy Trade-offs in Multi-Task Learning12h◆Predictive Training with Latent Imagination for Visual Quadruped Navigation12h◆Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making12h◆Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection12h◆Supervised Reward Inference12h◆PPO-HSC: An Exploratory Reinforcement Learning Framework Based on Wide-Area Policy Coverage Optimization12h◆Is Progressive Disclosure All You Need for Long-Context Agents?12h◆It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability12h◆DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification12h◆Oracle Gap and Signal Fidelity: A Fixed-Pool Diagnostic for Test-Time Collaboration12h◆Scientific reasoning does not reliably translate into scientific forecasting in frontier AI12h◆Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models12h◆AI-Augmented Human Resource Management? Insights from German companies12h◆
DataBubble·

Model Detail

dphn logo

dolphin-2.9-llama3-8b

—
Provider: dphnCategory: codePipeline: text-generationParameters: 8B
DB Score
34.6
Downloads
16K
Likes
481
Day
+0.0%
Week
+0.0%
Month
+0.0%
Overview

dolphin-2.9-llama3-8b is a code generation model with 8B parameters released by dphn. The model is registered under the text-generation pipeline tag on Hugging Face.

Performance

Open-LLM-Leaderboard scoring places it at MMLU-Pro 20, GPQA 5, IFEval 39, BBH 28, giving a sense of how it handles instruction following, reasoning, and graduate-level QA in absolute terms.

How we score this →
Technical

dolphin-2.9-llama3-8b ships as a LlamaForCausalLM / 💬 chat models (RLHF, DPO, IFT, ...) architecture with 8B parameters.

Use Cases

dolphin-2.9-llama3-8b is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.

Download History
Research Paper
arXiv: 2302.13971→
Benchmark Scores
IFEval
38.5
BBH
27.9
GPQA
4.9
MMLU-Pro
19.7
MATH
5.7
MUSR
13.8
Average
18.4
Model Info
ArchitectureLlamaForCausalLM
Type💬 chat models (RLHF, DPO, IFT, ...)
Citations20,091 (2105 influential)
Recent newsView all news →
Related News
arxiv70d ago

Dolphin-CN-Dialect: Where Chinese Dialects Matter

arXiv:2605.08961v1 Announce Type: new Abstract: We present Dolphin-CN-Dialect, a streaming-capable ASR model with a focus on Chinese and dialect-rich scenarios. Compared to the previous version, Dolphin-CN-Dialect introduces substantial improvements in data processing, tokenization, training stabili

Related Models
dphn logo
Dolphin-Mistral-24B-Venice-Edition
dphn · 133K downloads
dphn logo
Dolphin-X1-Trinity-Nano
dphn · 770 downloads
sentence-transformers logo
all-MiniLM-L6-v2
SBERT · 241.3M downloads
nomic-ai logo
nomic-embed-text-v1.5
nomic-ai · 17.1M downloads
HomeModelsNews