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

Cerebrum 1.0 8x7b by AetherResearch

 »  All LLMs  »  AetherResearch  »  Cerebrum 1.0 8x7b   URL Share it on

  30   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Conversational   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AetherResearch/Cerebrum-1.0-8x7b 

Cerebrum 1.0 8x7b Benchmarks

ARC: 68.09 vs 96.7 (so35)-29.6%
HellaSwag: 87.3 vs 95.3 (gpt4)-8.4%
MMLU: 72.45 vs 88.3 (so35)-18%
TruthfulQA: 50.63 vs 59 (gpt4)-14.2%
WinoGrande: 82.4 vs 87.5 (gpt4)-5.8%
GSM8K: 61.94 vs 96.4 (so35)-35.7%
LLME Score: 0.21015
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Cerebrum 1.0 8x7b Parameters and Internals

Model Type 
reasoning
Use Cases 
Areas:
reasoning, brainstorming, knowledge intensive, creative tasks
Primary Use Cases:
tasks that require reasoning
Training Details 
Data Sources:
native chain of thought data
Methodology:
fine-tuning on a small custom dataset and targeted RLHF
Input Output 
Input Format:
Alpaca-style template
Accepted Modalities:
text
Performance Tips:
Can be operated at very low temperatures for precise answers.
LLM NameCerebrum 1.0 8x7b
Repository 🤗https://huggingface.co/AetherResearch/Cerebrum-1.0-8x7b 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Model Size46.7b
Required VRAM93.6 GB
Updated2024-12-04
MaintainerAetherResearch
Model Typemixtral
Model Files  4.9 GB: 1-of-19   5.0 GB: 2-of-19   5.0 GB: 3-of-19   4.9 GB: 4-of-19   5.0 GB: 5-of-19   5.0 GB: 6-of-19   4.9 GB: 7-of-19   5.0 GB: 8-of-19   5.0 GB: 9-of-19   4.9 GB: 10-of-19   5.0 GB: 11-of-19   5.0 GB: 12-of-19   5.0 GB: 13-of-19   4.9 GB: 14-of-19   5.0 GB: 15-of-19   5.0 GB: 16-of-19   4.9 GB: 17-of-19   5.0 GB: 18-of-19   4.2 GB: 19-of-19
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16
Cerebrum 1.0 8x7b (AetherResearch/Cerebrum-1.0-8x7b)

Best Alternatives to Cerebrum 1.0 8x7b

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB2378754214
Nous Hermes 2 Mixtral 8x7B DPO32K / 93.6 GB3810420
Mixtral 8x7B V0.132K / 93.6 GB346611650
GritLM 8x7B KTO32K / 93.6 GB38223
...rkrautLM Mixtral 8x7B Instruct32K / 93.6 GB1924822
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB749801213
...enbuddy Mixtral 7bx8 V18.1 32K32K / 93.7 GB379714
Smaug Mixtral V0.132K / 187.7 GB387712
Merge Mixtral Prometheus 8x7B32K / 91.9 GB62
XLAM 8x7b R32K / 93.6 GB298511
Note: green Score (e.g. "73.2") means that the model is better than AetherResearch/Cerebrum-1.0-8x7b.

Rank the Cerebrum 1.0 8x7b 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? 38813 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 v20241124
  Support LLM Explorer