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

Chupacabra 8x7B MoE by perlthoughts

 »  All LLMs  »  perlthoughts  »  Chupacabra 8x7B MoE   URL Share it on

  1144   

Chupacabra 8x7B MoE is an open-source language model by perlthoughts. Features: 46.7b LLM, VRAM: 93.5GB, Context: 32K, License: apache-2.0, MoE, HF Score: 70.4, LLM Explorer Score: 0.13, Arc: 68.8, HellaSwag: 86.1, MMLU: 63.9, TruthfulQA: 63.5, WinoGrande: 80.5, GSM8K: 59.7.

  Autotrain compatible   Endpoints compatible   License:apache-2.0   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/perlthoughts/Chupacabra-8x7B-MoE 

Chupacabra 8x7B MoE Benchmarks

ARC: 68.77 vs 96.7 (so35)-28.9%
HellaSwag: 86.11 vs 95.3 (gpt4)-9.6%
MMLU: 63.86 vs 88.3 (so35)-27.7%
TruthfulQA: 63.5 vs 59 (gpt4)7.6%
WinoGrande: 80.51 vs 87.5 (gpt4)-8%
GSM8K: 59.67 vs 96.4 (so35)-38.1%
LLME Score: 0.1325
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chupacabra 8x7B MoE (perlthoughts/Chupacabra-8x7B-MoE)
🌟 Advertise your project 🚀

Chupacabra 8x7B MoE Parameters and Internals

LLM NameChupacabra 8x7B MoE
Repository 🤗https://huggingface.co/perlthoughts/Chupacabra-8x7B-MoE 
Model Size46.7b
Required VRAM93.5 GB
Updated2024-07-15
Maintainerperlthoughts
Model Typemixtral
Model Files  9.9 GB: 1-of-10   10.0 GB: 2-of-10   10.0 GB: 3-of-10   10.0 GB: 4-of-10   10.0 GB: 5-of-10   10.0 GB: 6-of-10   10.0 GB: 7-of-10   10.0 GB: 8-of-10   10.0 GB: 9-of-10   3.6 GB: 10-of-10
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Chupacabra 8x7B MoE

Model
Likes
Downloads
VRAM
Chupacabra 8x7B MoE GGUF312715 GB
Chupacabra 8x7B MoE GPTQ1923 GB

Best Alternatives to Chupacabra 8x7B MoE

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB4249854653
Nous Hermes 2 Mixtral 8x7B DPO32K / 93.6 GB8968452
Mixtral 8x7B V0.132K / 93.6 GB1210711799
Sensualize Mixtral Bf1632K / 93.6 GB00
Skadi Mixtral V132K / 93.5 GB00
Franziska Mixtral V132K / 93.5 GB00
Typhon Mixtral V132K / 93.4 GB00
GritLM 8x7B KTO32K / 93.6 GB82893
Smaug Mixtral V0.132K / 187.7 GB854812
XLAM 8x7b R32K / 93.6 GB6870815
Note: green Score (e.g. "73.2") means that the model is better than perlthoughts/Chupacabra-8x7B-MoE.

Rank the Chupacabra 8x7B MoE 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? 52509 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer