Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
nvidia 's Collections
Nemotron-H
Llama Nemotron
GEN3C
Model Optimizer
AceReason
Describe Anything
AceMath-RL
OpenMathReasoning
OpenCodeReasoning
OpenCodeReasoning-II
Llama Nemotron Feedback-Edit Inference-Time Scaling
Scoring Verifiers
Nemotron-UltraLong
Cosmos-Reason1
Cosmos-Transfer1
Cosmos-Tokenize1
Cosmos-Predict1
Cosmos-Tokenizer
Llama-3.1-Nemotron-70B
Physical AI
NVILA-Speech-Audio-Setups
QLIP
Cosmos
DMC
AceMath
NemoGuard
Eagle 2
NeMo Audio Codecs
Hymba
Optimized ONNX models for NVIDIA RTX GPUs
Riva
NVLM 1.0
OpenMath-2
Nemotron 4 340B
SteerLM
Parakeet
Canary
InstructRetro
OpenMath
RLHF
NV-Embed
Llama3-ChatQA-1.5
SSMs
Nemotron 3 8B
BigVGAN
MambaVision
PS3: Scaling Vision Pre-Training to 4K Resolution
Minitron
RADIO
Llama3-ChatQA-2
NeMo Curator - Classifier Models

Hymba

updated 2 days ago

A series of Hybrid Small Language Models.

Upvote
30

  • nvidia/Hymba-1.5B-Instruct

    Text Generation • Updated Jan 2 • 1.69k • 229

  • nvidia/Hymba-1.5B-Base

    Text Generation • Updated Jan 2 • 6.54k • 144

  • Hymba: A Hybrid-head Architecture for Small Language Models

    Paper • 2411.13676 • Published Nov 20, 2024 • 46
Upvote
30
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs