Mamba 2.8B Instruct Openhermes by clibrain

 ยป  All LLMs  ยป  clibrain  ยป  Mamba 2.8B Instruct Openhermes   URL Share it on

  Conversational   Dataset:teknium/openhermes   En   Endpoints compatible   Instruct   Pytorch   Region:us

Mamba 2.8B Instruct Openhermes Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mamba 2.8B Instruct Openhermes (clibrain/mamba-2.8b-instruct-openhermes)

Mamba 2.8B Instruct Openhermes Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model Card is still WIP!
Supported Languages 
en (Fluency level)
Training Details 
Data Sources:
GPTeacher - General Instruct, Roleplay v1, Roleplay v2, and Code Instruct Datasets, WizardLM (v1, evol_instruct 70k), Airoboros GPT-4 (v1.0), Camel-AI's domain expert datasets, CodeAlpaca, GPT4-LLM and Unnatural Instructions
Data Volume:
242,000 entries
Model Architecture:
Mamba - state space model architecture
Input Output 
Input Format:
text prompt via chat template
Accepted Modalities:
text
Output Format:
text
LLM NameMamba 2.8B Instruct Openhermes
Repository ๐Ÿค—https://huggingface.co/clibrain/mamba-2.8b-instruct-openhermes 
Model Size2.8b
Required VRAM5.5 GB
Updated2025-02-22
Maintainerclibrain
Instruction-BasedYes
Model Files  5.5 GB   5.5 GB   0.0 GB
Supported Languagesen
Model ArchitectureAutoModel
Licensewtfpl
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|endoftext|>
Vocabulary Size50277

Rank the Mamba 2.8B Instruct Openhermes Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227