LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2   URL Share it on

  6   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Conversational   Distillation   En   Endpoints compatible   Exl2   Finetuned   Gpt4   Instruct   Llama   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow

OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2 Benchmarks

LLME Score: 0.16589
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2 Parameters and Internals

Model Type 
Mixtral, Instruct, Finetune
Use Cases 
Areas:
text generation, conversational AI
Considerations:
Designed for multi-turn conversations and setting system prompts
Additional Notes 
Image associated in the documentation may relate to visual branding
Supported Languages 
en (full proficiency)
Training Details 
Data Sources:
OpenHermes dataset
Methodology:
Fine-tuning
Training Time:
3 epochs
Model Architecture:
Based on LLaMA-2
Input Output 
Input Format:
LLaMA-2 prompt template
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Multi-turn conversations and system prompt setups enhance effectiveness
LLM NameOpenHermes Mixtral 8x7B 2.4bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/OpenHermes-Mixtral-8x7B-2.4bpw-h6-exl2 
Base Model(s)  mistralai/Mixtral-8x7B-Instruct-v0.1   mistralai/Mixtral-8x7B-Instruct-v0.1
Required VRAM14.3 GB
Updated2024-11-22
MaintainerLoneStriker
Model Typemixtral
Instruction-BasedYes
Model Files  8.6 GB: 1-of-2   5.7 GB: 2-of-2
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16
OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2 (LoneStriker/OpenHermes-Mixtral-8x7B-2.4bpw-h6-exl2)

Best Alternatives to OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...M 2 8x22B Beige 3.0bpw H6 EXL264K / 53.2 GB100
...M 2 8x22B Beige 2.4bpw H6 EXL264K / 42.7 GB60
...M 2 8x22B Beige 4.0bpw H6 EXL264K / 70.8 GB50
...M 2 8x22B Beige 5.0bpw H6 EXL264K / 88.5 GB50
...B Instruct V0.1 8.0bpw H8 EXL264K / 120.2 GB31
...8x22b Instruct Oh EXL2 2.25bpw64K / 40.1 GB31
...eryTour V2 8x7B 4.5bpw H6 EXL232K / 26.5 GB132
...it MoE 2bitgs8 Metaoffload HQQ32K / 24.1 GB1020
... 4bit MoE 2bit Metaoffload HQQ32K / 18.3 GB3615
... 4bit MoE 3bit Metaoffload HQQ32K / 22.4 GB613
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/OpenHermes-Mixtral-8x7B-2.4bpw-h6-exl2.

Rank the OpenHermes Mixtral 8x7B 2.4bpw H6 EXL2 Capabilities

🆘 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! 🌟

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? 38200 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110
  Support LLM Explorer