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

Mixtral 8x22b Instruct Oh EXL2 2.25bpw by Dracones

 »  All LLMs  »  Dracones  »  Mixtral 8x22b Instruct Oh EXL2 2.25bpw   URL Share it on

  4   
  Autotrain compatible Base model:mistral-community/m...   Conversational   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Exl2   Instruct   License:apache-2.0   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Mixtral 8x22b Instruct Oh EXL2 2.25bpw Benchmarks

HF Avg Score: 65.3  vs  86.1  (GPT-4) -24.2%
ARC: 62-35.6%
HellaSwag: 74.5-21.8%
MMLU: 68.5-20.8%
TruthfulQA: 49-16.9%
WinoGrande: 82.8-5.4%
GSM8K: 53.4-42%
nn.n% — How the model compares to the GPT-4.

Rank the Mixtral 8x22b Instruct Oh EXL2 2.25bpw 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  
Mixtral 8x22b Instruct Oh EXL2 2.25bpw (Dracones/mixtral-8x22b-instruct-oh_exl2_2.25bpw)

Best Alternatives to Mixtral 8x22b Instruct Oh EXL2 2.25bpw

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...es Mixtral 8x7B 2.4bpw H6 EXL263.732K / 14.3 GB12
...es Mixtral 8x7B 3.0bpw H6 EXL263.732K / 17.8 GB11
Notux 8x7b V1.3.5bpw EXL263.732K / 20.7 GB12
Notux 8x7b V1.3.5bpw H6 EXL263.732K / 20.7 GB11
...es Mixtral 8x7B 6.0bpw H6 EXL263.732K / 35.3 GB11
...ixtral 8x7B Instruct V0.1 GGUF63.732K / 17.3 GB4995
...M 2 8x22B Beige 2.4bpw H6 EXL2—64K / 42.7 GB60
...M 2 8x22B Beige 3.0bpw H6 EXL2—64K / 53.2 GB150
...M 2 8x22B Beige 4.0bpw H6 EXL2—64K / 70.8 GB860
...M 2 8x22B Beige 5.0bpw H6 EXL2—64K / 88.5 GB100

Mixtral 8x22b Instruct Oh EXL2 2.25bpw Parameters and Internals

LLM NameMixtral 8x22b Instruct Oh EXL2 2.25bpw
RepositoryOpen on 🤗 
Base Model(s)  Mixtral 8x22B V0.1   mistral-community/Mixtral-8x22B-v0.1
Required VRAM40.1 GB
Updated2024-07-01
MaintainerDracones
Model Typemixtral
Instruction-BasedYes
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.6 GB: 3-of-5   8.6 GB: 4-of-5   5.7 GB: 5-of-5
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 34238 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 v2024042801
  Support LLM Explorer