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

Rawr by beberik

 »  All LLMs  »  beberik  »  Rawr   URL Share it on

  1302   

Rawr is an open-source language model by beberik. Features: 7b LLM, VRAM: 93.5GB, Context: 32K, License: cc-by-nc-4.0, HF Score: 67.2, LLM Explorer Score: 0.14, Arc: 64, HellaSwag: 84.9, MMLU: 64.7, TruthfulQA: 52.1, WinoGrande: 79.6, GSM8K: 58.1.

  Autotrain compatible   Conversational   Endpoints compatible   Merge   Mixtral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/beberik/rawr 

Rawr Benchmarks

ARC: 63.99 vs 96.7 (so35)-33.8%
HellaSwag: 84.86 vs 95.3 (gpt4)-11%
MMLU: 64.7 vs 88.3 (so35)-26.7%
TruthfulQA: 52.07 vs 59 (gpt4)-11.7%
WinoGrande: 79.56 vs 87.5 (gpt4)-9.1%
GSM8K: 58.07 vs 96.4 (so35)-39.8%
LLME Score: 0.13801
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rawr (beberik/rawr)
🌟 Advertise your project 🚀

Rawr Parameters and Internals

Model Type 
text-generation
Additional Notes 
Another experiment with moe merge. Prompt template: Just use chatml. Or alpaca. Or any you like. Maybe it will work. I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here.
LLM NameRawr
Repository 🤗https://huggingface.co/beberik/rawr 
Model Size7b
Required VRAM93.5 GB
Updated2024-12-02
Maintainerbeberik
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
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Rawr

Best Alternatives
Context / RAM
Downloads
Likes
Multimaster 7B V632K / 142.5 GB84281
MultiverseBuddy 15B MoE32K / 25.8 GB90
Mini Mixtral V0.232K / 25.8 GB64
Multilingual Mistral32K / 93.5 GB7242
OpenMistral MoE32K / 48.3 GB12180
Lumina 232K / 37.1 GB90
Laserxtral32K / 48.3 GB81078
Merged Model MoE32K / 53.3 GB51
RogerWizard 12B MoE32K / 25.8 GB41
StarlingMaths 12B MoE32K / 25.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than beberik/rawr.

Rank the Rawr 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? 52473 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