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

Llama 3 Smaug 8B by abacusai

 »  All LLMs  »  abacusai  »  Llama 3 Smaug 8B   URL Share it on

  9272   
  Arxiv:2402.13228   Autotrain compatible   Conversational Dataset:anon8231489123/sharegp...   Dataset:aqua rat Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/abacusai/Llama-3-Smaug-8B 

Llama 3 Smaug 8B Benchmarks

MMLU Pro: 24.28
MUSR: 5.05
BBH: 27.88
IFEval: 48.67 vs 88 (so35)-44.7%
ARC: 59.56 vs 96.7 (so35)-38.4%
HellaSwag: 80.04 vs 95.3 (gpt4)-16%
MMLU: 65.77 vs 88.3 (so35)-25.5%
TruthfulQA: 51.67 vs 59 (gpt4)-12.4%
WinoGrande: 74.74 vs 87.5 (gpt4)-14.6%
GSM8K: 55.88 vs 96.4 (so35)-42%
MATH Lvl 5: 8.53
LLME Score: 0.29495
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Smaug 8B (abacusai/Llama-3-Smaug-8B)

Llama 3 Smaug 8B Parameters and Internals

Model Type 
text generation
Additional Notes 
This version of Smaug uses new techniques and new data compared to Smaug-72B, and more information will be released later.
Training Details 
Data Sources:
aqua_rat, microsoft/orca-math-word-problems-200k, m-a-p/CodeFeedback-Filtered-Instruction, anon8231489123/ShareGPT_Vicuna_unfiltered
Methodology:
Smaug recipe for improving performance on real-world multi-turn conversations
LLM NameLlama 3 Smaug 8B
Repository 🤗https://huggingface.co/abacusai/Llama-3-Smaug-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-04-25
Maintainerabacusai
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
Licensellama2
Context Length8192
Model Max Length8192
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3 Smaug 8B

Model
Likes
Downloads
VRAM
Llama 3 Smaug 8B GGUF4125383 GB
Smaugredq0384 GB
Llama 3 Smaug 8B AWQ125 GB
Llama 3 Smaug 8B 4bit1165 GB
Smaugredq004 GB

Best Alternatives to Llama 3 Smaug 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3199101
UltraLong Thinking4192K / 16.1 GB652
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB125015
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB282439
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB141
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB26334679
A11024K / 16.1 GB8530
Note: green Score (e.g. "73.2") means that the model is better than abacusai/Llama-3-Smaug-8B.

Rank the Llama 3 Smaug 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? 46715 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 v20241227
  Support LLM Explorer