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

UNA SimpleSmaug 34B V1beta by fblgit

 »  All LLMs  »  fblgit  »  UNA SimpleSmaug 34B V1beta   URL Share it on

  3060   
  Autotrain compatible Base model:abacusai/smaug-34b-... Base model:finetune:abacusai/s...   Conversational   Dataset:fblgit/simple-math   Dataset:jondurbin/bagel-v0.3   Endpoints compatible   Juanako   Llama   Model-index   Region:us   Safetensors   Sharded   Simple-math   Tensorflow   Una
Model Card on HF 🤗: https://huggingface.co/fblgit/UNA-SimpleSmaug-34b-v1beta 

UNA SimpleSmaug 34B V1beta Benchmarks

MMLU Pro: 39.33
GPQA: 8.95
MUSR: 11.96
BBH: 32.78
IFEval: 45.56 vs 88 (so35)-48.2%
ARC: 74.57 vs 96.7 (so35)-22.9%
HellaSwag: 86.74 vs 95.3 (gpt4)-9%
MMLU: 76.68 vs 88.3 (so35)-13.2%
TruthfulQA: 70.17 vs 59 (gpt4)18.9%
WinoGrande: 83.82 vs 87.5 (gpt4)-4.2%
GSM8K: 72.48 vs 96.4 (so35)-24.8%
MATH Lvl 5: 0.15
LLME Score: 0.27994
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
UNA SimpleSmaug 34B V1beta (fblgit/UNA-SimpleSmaug-34b-v1beta)

UNA SimpleSmaug 34B V1beta Parameters and Internals

Model Type 
text-generation
Additional Notes 
Applied UNA only on the Attention, not on the MLP's. Increasing GSM, MMLU, ARC, WINO.
Training Details 
Data Sources:
fblgit/simple-math, jondurbin/bagel-v0.3
Methodology:
SimpleMath applied at the attention layer during a SFT session
LLM NameUNA SimpleSmaug 34B V1beta
Repository 🤗https://huggingface.co/fblgit/UNA-SimpleSmaug-34b-v1beta 
Base Model(s)  abacusai/Smaug-34B-v0.1   abacusai/Smaug-34B-v0.1
Model Size34b
Required VRAM69.2 GB
Updated2024-12-21
Maintainerfblgit
Model Typellama
Model Files  4.8 GB: 1-of-15   4.8 GB: 2-of-15   5.0 GB: 3-of-15   4.8 GB: 4-of-15   4.8 GB: 5-of-15   5.0 GB: 6-of-15   4.8 GB: 7-of-15   4.8 GB: 8-of-15   5.0 GB: 9-of-15   4.8 GB: 10-of-15   4.8 GB: 11-of-15   5.0 GB: 12-of-15   4.8 GB: 13-of-15   4.8 GB: 14-of-15   1.2 GB: 15-of-15
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to UNA SimpleSmaug 34B V1beta

Best Alternatives
Context / RAM
Downloads
Likes
Casual Magnum 34B195K / 68.8 GB131
34B Beta195K / 69.2 GB354862
Yi 34B 200K195K / 68.9 GB4525317
Smaug 34B V0.1195K / 69.2 GB371860
Bagel Hermes 34B Slerp195K / 68.9 GB39861
Bagel 34B V0.2195K / 68.7 GB395439
Yi 34B 200K AEZAKMI V2195K / 69.2 GB121012
Smaug 34B V0.1 ExPO195K / 69.2 GB29660
Faro Yi 34B195K / 69.2 GB37496
Bagel DPO 34B V0.5195K / 68.7 GB300817
Note: green Score (e.g. "73.2") means that the model is better than fblgit/UNA-SimpleSmaug-34b-v1beta.

Rank the UNA SimpleSmaug 34B V1beta 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? 40013 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