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

Jaskier 7B DPO V5.6 by bardsai

 »  All LLMs  »  bardsai  »  Jaskier 7B DPO V5.6   URL Share it on

  187   
  7b   Autotrain compatible Dataset:argilla/distilabel-mat...   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6 

Jaskier 7B DPO V5.6 Benchmarks

ARC: 73.04 vs 96.7 (so35)-24.5%
HellaSwag: 89 vs 95.3 (gpt4)-6.6%
MMLU: 64.38 vs 88.3 (so35)-27.1%
TruthfulQA: 77.81 vs 59 (gpt4)31.9%
WinoGrande: 84.53 vs 87.5 (gpt4)-3.4%
GSM8K: 69.67 vs 96.4 (so35)-27.7%
LLME Score: 0.19155
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jaskier 7B DPO V5.6 (bardsai/jaskier-7b-dpo-v5.6)

Jaskier 7B DPO V5.6 Parameters and Internals

Model Type 
llm
Use Cases 
Areas:
nlp, machine vision, time series analysis
Additional Notes 
This is a work-in-progress model, may not be ready for production use.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
argilla/distilabel-math-preference-dpo
Methodology:
Direct Preference Optimization
Release Notes 
Version:
v5.6
Date:
2024-02-16
Notes:
Initial release
LLM NameJaskier 7B DPO V5.6
Repository 🤗https://huggingface.co/bardsai/jaskier-7b-dpo-v5.6 
Model Size7b
Required VRAM14.4 GB
Updated2024-12-14
Maintainerbardsai
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Jaskier 7B DPO V5.6

Model
Likes
Downloads
VRAM
Jaskier 7B DPO V5.6 GGUF4832 GB

Best Alternatives to Jaskier 7B DPO V5.6

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB27459
MegaBeam Mistral 7B 512K512K / 14.4 GB1839147
SpydazWeb AI HumanAI RP512K / 14.4 GB361
SpydazWeb AI HumanAI 002512K / 14.4 GB161
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB334815
Hebrew Mistral 7B 200K256K / 30 GB338615
Astral 256K 7B V2250K / 14.4 GB180
Astral 256K 7B250K / 14.4 GB110
Boptruth Agatha 7B128K / 14.4 GB6090
Note: green Score (e.g. "73.2") means that the model is better than bardsai/jaskier-7b-dpo-v5.6.

Rank the Jaskier 7B DPO V5.6 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? 39237 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 v20241124
  Support LLM Explorer