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

UNA TheBeagle 7B V1 by fblgit

 »  All LLMs  »  fblgit  »  UNA TheBeagle 7B V1   URL Share it on

  1260   
  Autotrain compatible   Dataset:jondurbin/bagel-v0.3   Endpoints compatible   Generated from trainer   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1 

UNA TheBeagle 7B V1 Benchmarks

MMLU Pro: 22.44
GPQA: 4.59
MUSR: 16.09
BBH: 30.17
IFEval: 36.89 vs 88 (so35)-58.1%
ARC: 73.04 vs 96.7 (so35)-24.5%
HellaSwag: 88 vs 95.3 (gpt4)-7.7%
MMLU: 63.48 vs 88.3 (so35)-28.1%
TruthfulQA: 69.85 vs 59 (gpt4)18.4%
WinoGrande: 82.16 vs 87.5 (gpt4)-6.1%
GSM8K: 66.72 vs 96.4 (so35)-30.8%
MATH Lvl 5: 7.63
LLME Score: 0.24505
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
UNA TheBeagle 7B V1 (fblgit/UNA-TheBeagle-7b-v1)

UNA TheBeagle 7B V1 Parameters and Internals

Additional Notes 
UNA applied over a set of curated DPO pairs.
Training Details 
Data Sources:
jondurbin/bagel-v0.3
Methodology:
Applied UNA thru the perceptrons at a speed of 3.5e-7
Input Output 
Input Format:
Vanilla version of the bagel training code, flexible with prompt formats
Performance Tips:
A good model should generalize with different prompt formats.
LLM NameUNA TheBeagle 7B V1
Repository 🤗https://huggingface.co/fblgit/UNA-TheBeagle-7b-v1 
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
Maintainerfblgit
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-nd-4.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the UNA TheBeagle 7B V1

Model
Likes
Downloads
VRAM
UNA TheBeagle 7B V1 GGUF185942 GB
UNA TheBeagle 7B V1 GPTQ31174 GB
UNA TheBeagle 7B V1 AWQ1664 GB

Best Alternatives to UNA TheBeagle 7B V1

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
MegaBeam Mistral 7B 512K512K / 14.4 GB655449
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB647215
Hebrew Mistral 7B 200K256K / 30 GB489915
Astral 256K 7B V2250K / 14.4 GB60
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than fblgit/UNA-TheBeagle-7b-v1.

Rank the UNA TheBeagle 7B V1 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? 42577 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