-
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Paper • 2610.28578 • Published • 71 -
InternScience/Sage-A1.5
Text Generation • 36B • Updated • 25.7k • 411 -
InternScience/Sage-A1.5-FP8
Text Generation • 36B • Updated • 1.9k • 14 -
InternScience/Sage-A1.5-Q4_K_M-GGUF
Text Generation • 36B • Updated • 756k • 85
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
Organization Card
Welcome to the InternScience organization, the open-source hub of AI for Science Center @Shanghai AI Laboratory. We focus on open-sourcing high quality LLMs/MLLMs, tools, and datasets to accelerate scientific discovery across disciplines.
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Paper • 2606.30616 • Published • 103 -
InternScience/Agents-A1
Text Generation • 35B • Updated • 2.6k • 671 -
InternScience/Agents-A1-FP8
Text Generation • 35B • Updated • 182 • 25 -
InternScience/Agents-A1-Q4_K_M-GGUF
Text Generation • 35B • Updated • 8.1k • 155
-
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Paper • 2610.28578 • Published • 71 -
InternScience/Sage-A1.5
Text Generation • 36B • Updated • 25.7k • 411 -
InternScience/Sage-A1.5-FP8
Text Generation • 36B • Updated • 1.9k • 14 -
InternScience/Sage-A1.5-Q4_K_M-GGUF
Text Generation • 36B • Updated • 756k • 85
Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Paper • 2606.30616 • Published • 103 -
InternScience/Agents-A1
Text Generation • 35B • Updated • 2.6k • 671 -
InternScience/Agents-A1-FP8
Text Generation • 35B • Updated • 182 • 25 -
InternScience/Agents-A1-Q4_K_M-GGUF
Text Generation • 35B • Updated • 8.1k • 155
spaces 5
pinned
Running
Agents
10
SGI-Bench Leaderboard
🥇
Scientific General Intelligence of LLMs/vLLMs
pinned
Paused
Agents
4
SciEval Leaderboard
🥇
Open, science-focus leaderboards benchmarking LLMs and VLMs
Running
6
ResearchHarness
🚀
Lightweight harness for tool-using LLM agents.
Sleeping
Agents
1
ResearchClawBench Task Submission
📦
Validate and submit a ResearchClawBench task ZIP to Hugging Face
models 22
InternScience/Sage-A1.5-F16-GGUF
Text Generation • 36B • Updated • 12.8k • 8
InternScience/Sage-A1.5-Q8_0-GGUF
Text Generation • 36B • Updated • 688k • 17
InternScience/Sage-A1.5-Q6_K-GGUF
Text Generation • 36B • Updated • 5.97k • 3
InternScience/Sage-A1.5-Q4_K_M-GGUF
Text Generation • 36B • Updated • 756k • 85
InternScience/Sage-A1.5-FP8
Text Generation • 36B • Updated • 1.9k • 14
InternScience/Sage-A1.5
Text Generation • 36B • Updated • 25.7k • 411
InternScience/MLExpert
Text Generation • 35B • Updated • 3.2k • 17
InternScience/Agents-A1
Text Generation • 35B • Updated • 2.6k • 671
InternScience/Agents-A1-F16-GGUF
Text Generation • 35B • Updated • 149 • 14
InternScience/Agents-A1-Q8_0-GGUF
Text Generation • 35B • Updated • 313 • 38
datasets 23
InternScience/ResearchClawBench
Benchmark • Updated • 57 • 14.2k • 16
InternScience/Agents-A1-ifstruct-eval-20260703-041434
Preview • Updated • 47 • 1
InternScience/Scholar-kg
Updated • 124 • 9
InternScience/SGI-Reasoning-Lite
Viewer • Updated • 72 • 82 • 1
InternScience/SGI-DryExperiment-Lite
Viewer • Updated • 67 • 95 • 1
InternScience/SGI-IdeaGeneration-Lite
Viewer • Updated • 78 • 85 • 1
InternScience/SGI-DeepResearch-Lite
Viewer • Updated • 60 • 113 • 2
InternScience/SGI-DeepResearch-Gold
Viewer • Updated • 243 • 135 • 4
InternScience/SGI-Reasoning
Viewer • Updated • 291 • 222 • 8
InternScience/SGI-WetExperiment
Viewer • Updated • 68 • 241 • 4