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

Daredevil 8B by mlabonne

 »  All LLMs  »  mlabonne  »  Daredevil 8B   URL Share it on

  142   
  Autotrain compatible Base model:cstr/llama3-8b-spae... Base model:flammenai/mahou-1.1... Base model:hastagaras/llama-3-... Base model:kingnish/kingnish-l... Base model:kukedlc/neuralllama... Base model:merge:cstr/llama3-8... Base model:merge:flammenai/mah... Base model:merge:hastagaras/ll... Base model:merge:kingnish/king... Base model:merge:kukedlc/neura... Base model:merge:mlabonne/chim... Base model:merge:nbeerbower/ll... Base model:merge:nbeerbower/ll... Base model:merge:openchat/open... Base model:mlabonne/chimeralla... Base model:nbeerbower/llama-3-... Base model:nbeerbower/llama-3-... Base model:openchat/openchat-3...   Conversational   Endpoints compatible   Lazymergekit   Llama   Merge   Mergekit   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/Daredevil-8B 

Daredevil 8B Benchmarks

MMLU Pro: 31.45
GPQA: 7.72
MUSR: 7.53
BBH: 31.63
IFEval: 45.48 vs 88 (so35)-48.3%
ARC: 68.86 vs 96.7 (so35)-28.8%
HellaSwag: 84.5 vs 95.3 (gpt4)-11.3%
MMLU: 69.24 vs 88.3 (so35)-21.6%
TruthfulQA: 59.89 vs 59 (gpt4)1.5%
WinoGrande: 78.45 vs 87.5 (gpt4)-10.3%
GSM8K: 73.54 vs 96.4 (so35)-23.7%
MATH Lvl 5: 10.05
LLME Score: 0.28684
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Daredevil 8B (mlabonne/Daredevil-8B)

Daredevil 8B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Daredevil-8B is a mega-merge designed to maximize MMLU. It uses MergeKit for merging various models.
LLM NameDaredevil 8B
Repository 🤗https://huggingface.co/mlabonne/Daredevil-8B 
Base Model(s)  Llama 3 Stella 8B   Hastagaras/llama-3-8b-okay   Llama 3 Gutenberg 8B   openchat/openchat-3.6-8b-20240522   Kukedlc/NeuralLLaMa-3-8b-DT-v0.1   Llama3 8B Spaetzle V20   ChimeraLlama 3 8B V3   flammenai/Mahou-1.1-llama3-8B   KingNish Llama3 8B   nbeerbower/llama-3-stella-8B   Hastagaras/llama-3-8b-okay   nbeerbower/llama-3-gutenberg-8B   openchat/openchat-3.6-8b-20240522   Kukedlc/NeuralLLaMa-3-8b-DT-v0.1   cstr/llama3-8b-spaetzle-v20   mlabonne/ChimeraLlama-3-8B-v3   flammenai/Mahou-1.1-llama3-8B   KingNish/KingNish-Llama3-8b
Model Size8b
Required VRAM16.1 GB
Updated2024-12-22
Maintainermlabonne
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Daredevil 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB4850678
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
MrRoboto ProLong 8B V2b1024K / 16.1 GB1770
MrRoboto ProLong 8B V4b1024K / 16.1 GB940
MrRoboto ProLong 8B V1n1024K / 16.1 GB1560
MrRoboto ProLong 8B V4c1024K / 16.1 GB790
MrRoboto ProLong 8B V4e1024K / 16.1 GB430
MrRoboto ProLong 8B V1a1024K / 16.1 GB1070
HEL V0.8 8B LONG DARK1024K / 16.1 GB2000
MrRoboto ProLong 8B V2a1024K / 16.1 GB1010
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/Daredevil-8B.

Rank the Daredevil 8B 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? 40066 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 v20241217
  Support LLM Explorer