vanta research
- 4 followers
- United States of America
- https://vantaresearch.xyz
- https://huggingface.co/vanta-research
- hello@vantaresearch.xyz
Popular repositories Loading
-
apollo-v1-7b
apollo-v1-7b PublicApollo V1 7B is a specialized language model designed for advanced reasoning tasks, including logical reasoning, mathematical problem-solving, and legal analysis. Built on Mistral 7B-Instruct-v0.3 …
-
human-ai-collaboration-1
human-ai-collaboration-1 PublicA curated, high-quality synthetically generated dataset of human-AI conversational exchanges designed for training and evaluating AI models on collaborative reasoning, problem-solving, and knowledg…
-
apollo-astralis-8b
apollo-astralis-8b PublicApollo Astralis brings frontier-level reasoning in a warm, collaborative tone to OSS architecture on edge devices
Jinja
-
human-ai-collaboration-2
human-ai-collaboration-2 PublicDataset for LoRA training containing ~6,320 high quality human-AI collaboration examples
Repositories
- vrre Public
VANTA Research Reasoning Evaluation is a novel reasoning benchmark that displays differences in reasoning quality often missed by standard benchmarks.
vanta-research/vrre’s past year of commit activity - human-ai-collaboration-2 Public
Dataset for LoRA training containing ~6,320 high quality human-AI collaboration examples
vanta-research/human-ai-collaboration-2’s past year of commit activity - human-ai-collaboration-1 Public
A curated, high-quality synthetically generated dataset of human-AI conversational exchanges designed for training and evaluating AI models on collaborative reasoning, problem-solving, and knowledge synthesis.
vanta-research/human-ai-collaboration-1’s past year of commit activity - apollo-astralis-8b Public
Apollo Astralis brings frontier-level reasoning in a warm, collaborative tone to OSS architecture on edge devices
vanta-research/apollo-astralis-8b’s past year of commit activity - apollo-v1-7b Public
Apollo V1 7B is a specialized language model designed for advanced reasoning tasks, including logical reasoning, mathematical problem-solving, and legal analysis. Built on Mistral 7B-Instruct-v0.3 using LoRA fine-tuning, this model represents the first public release in the Apollo model series from VANTA Research.
vanta-research/apollo-v1-7b’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…