Nous Hermes 2 Mixtral 8x7B DPO 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Nous Hermes 2 Mixtral 8x7B DPO 4bit   URL Share it on

  4bit Base model:mistralai/mixtral-8...   Chatml   Distillation   Dpo   En   Finetuned   Gpt4   Instruct   License:apache-2.0   Mixtral   Mlx   Moe   Quantized   Region:us   Rlhf   Synthetic data

Nous Hermes 2 Mixtral 8x7B DPO 4bit Parameters and Internals

LLM NameNous Hermes 2 Mixtral 8x7B DPO 4bit
RepositoryOpen on ๐Ÿค— 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Required VRAM10.6 GB
Updated2024-07-19
Maintainermlx-community
Model Typemixtral
Model Files  16.1 GB   10.6 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16
Nous Hermes 2 Mixtral 8x7B DPO 4bit (mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit)

Best Alternatives to Nous Hermes 2 Mixtral 8x7B DPO 4bit

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...oE V0.1 DPO F16 4.0bpw H6 EXL2195K / 31.3 GB00
...oE V0.1 DPO F16 5.0bpw H6 EXL2195K / 38.8 GB00
...M 2 8x22B Beige 4.0bpw H6 EXL20.364K / 70.8 GB890
...2 Mixtral 8x22b 6.0bpw H8 EXL20.264K / 105.8 GB131
WizardLM 2 8x22 EXL2 4.0bpw0.264K / 70.9 GB61
...M 2 8x22B Beige 3.0bpw H6 EXL20.264K / 53.2 GB190
...M 2 8x22B Beige 5.0bpw H6 EXL20.264K / 88.5 GB140
...M 2 8x22B Beige 2.4bpw H6 EXL20.264K / 42.7 GB100
...2 Mixtral 8x22b 8.0bpw H8 EXL20.264K / 125.1 GB132
...B Instruct V0.1 8.0bpw H8 EXL20.264K / 120.2 GB91
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nous-Hermes-2-Mixtral-8x7B-DPO-4bit.

Rank the Nous Hermes 2 Mixtral 8x7B DPO 4bit 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? 34211 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601