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

Orangetin OpenHermes Mixtral 8x7B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Orangetin OpenHermes Mixtral 8x7B GPTQ   URL Share it on

  603   
  4-bit   Autotrain compatible Base model:orangetin/openherme... Base model:quantized:orangetin...   Conversational   Distillation   En   Finetuned   Gpt4   Gptq   Instruct   Llama   Mixtral   Moe   Quantized   Region:us   Safetensors   Synthetic data
Model Card on HF 🤗: https://huggingface.co/TheBloke/orangetin-OpenHermes-Mixtral-8x7B-GPTQ 

Orangetin OpenHermes Mixtral 8x7B GPTQ Benchmarks

LLME Score: 0.16734
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orangetin OpenHermes Mixtral 8x7B GPTQ (TheBloke/orangetin-OpenHermes-Mixtral-8x7B-GPTQ)

Orangetin OpenHermes Mixtral 8x7B GPTQ Parameters and Internals

Model Type 
mixtral, instruct, finetune, llama, gpt4, synthetic data, distillation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Quantisation reduces VRAM usage with minimal loss in inference accuracy.
Supported Languages 
English (Fluent)
Training Details 
Data Sources:
OpenHermes dataset, teknium dataset
Data Volume:
3 epochs
Methodology:
Finetuning on mixtral model
Context Length:
8192
Hardware Used:
Together AI compute access
Model Architecture:
Mixtral architecture
Input Output 
Input Format:
[INST] <> {system_message} <> {prompt} [/INST]
Accepted Modalities:
text
Output Format:
Text-generation outputs
Performance Tips:
Use compatible servers/webuis for optimal performance.
Release Notes 
Version:
1.0
Date:
2023-10
Notes:
Initial release of the quantised 8X7B model, with multiple quantisation options for different hardware and accuracy requirements.
LLM NameOrangetin OpenHermes Mixtral 8x7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/orangetin-OpenHermes-Mixtral-8x7B-GPTQ 
Model NameOrangetin OpenHermes Mixtral 8X7B
Model CreatorOrangeTin
Base Model(s)  OpenHermes Mixtral 8x7B   orangetin/OpenHermes-Mixtral-8x7B
Model Size6.1b
Required VRAM23.8 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemixtral
Model Files  23.8 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Orangetin OpenHermes Mixtral 8x7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x7B Instruct V0.1 GPTQ32K / 23.8 GB55564135
Mixtral 8x7B V0.1 GPTQ32K / 23.8 GB512127
...Hermes 2 Mixtral 8x7B DPO GPTQ32K / 23.8 GB18126
Dolphin 2.5 Mixtral 8x7b GPTQ32K / 23.8 GB143109
...Hermes 2 Mixtral 8x7B SFT GPTQ32K / 23.8 GB4011
...tLM Mixtral 8x7B Instruct GPTQ32K / 23.8 GB2433
Bagel DPO 8x7b V0.2 GPTQ32K / 23.8 GB112
...xtral Instruct 8x7b Zloss GPTQ32K / 23.8 GB252
Open Gpt4 8x7B V0.2 GPTQ32K / 23.8 GB126
Sensualize Mixtral GPTQ32K / 23.8 GB275
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/orangetin-OpenHermes-Mixtral-8x7B-GPTQ.

Rank the Orangetin OpenHermes Mixtral 8x7B GPTQ 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? 42577 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 v20241227
  Support LLM Explorer