Hermes 2 Pro Mistral 7B by NousResearch

 ยป  All LLMs  ยป  NousResearch  ยป  Hermes 2 Pro Mistral 7B   URL Share it on

  Autotrain compatible Base model:mistralai/mistral-7...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Distillation   Dpo   En   Endpoints compatible   Finetuned   Function calling   Gpt4   Has space   Instruct   Json mode   License:apache-2.0   Mistral   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow

Hermes 2 Pro Mistral 7B Benchmarks

Rank the Hermes 2 Pro Mistral 7B 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  
Hermes 2 Pro Mistral 7B (NousResearch/Hermes-2-Pro-Mistral-7B)

Quantized Models of the Hermes 2 Pro Mistral 7B

Hermes 2 Pro Mistral 7B AWQ0424 GB
...Mistral 7B Metropole 4bit Gguf0284 GB
...AL Dqg 2024 03 27 16bit Merged0614 GB

Best Alternatives to Hermes 2 Pro Mistral 7B

Best Alternatives
HF Rank
...nated Proof 7b V1.0 Safetensor81.144K / 14.4 GB140510
Contaminated Proof 7b V1.081.144K / 14.4 GB13104
YamshadowExperiment28 7B76.8632K / 14.4 GB173015
M7 7B76.8232K / 14.4 GB746211
MultiverseEx26 7B Slerp76.832K / 14.4 GB7760
NeuralSynthesis 7B V0.176.832K / 14.5 GB11321
Percival 01 7B Slerp76.7932K / 14.4 GB25442
...periment27Multi Verse Model 7B76.7732K / 14.4 GB10950
NeuralSynthesis 7B V0.4 Slerp76.7632K / 14.5 GB3300
Maxine 7B 0401 Stock76.7332K / 14.4 GB12101
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Hermes-2-Pro-Mistral-7B.

Hermes 2 Pro Mistral 7B Parameters and Internals

LLM NameHermes 2 Pro Mistral 7B
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Mistral 7B V0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM14.5 GB
Model Typemistral
Model Files  4.0 GB: 1-of-4   3.9 GB: 2-of-4   3.9 GB: 3-of-4   2.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32032
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 35526 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20240042001