Bagel DPO 7B V0.1 by jondurbin

 ยป  All LLMs  ยป  jondurbin  ยป  Bagel DPO 7B V0.1   URL Share it on

  Autotrain compatible   Conversational   Dataset:ai2 arc Dataset:allenai/ultrafeedback ...   Dataset:boolq   Dataset:cais/mmlu   Dataset:cakiki/rosetta-code   Dataset:codeparrot/apps   Dataset:datasets/winogrande   Dataset:drop   Dataset:facebook/belebele   Dataset:intel/orca dpo pairs Dataset:jondurbin/cinematika-v... Dataset:jondurbin/truthy-dpo-v...   Dataset:lmsys/lmsys-chat-1m Dataset:migtissera/synthia-v1.... Dataset:muennighoff/natural-in...   Dataset:nvidia/helpsteer   Dataset:open-orca/slimorca   Dataset:openbookqa   Dataset:piqa   Dataset:spider   Dataset:squad v2   Dataset:tiger-lab/mathinstruct   Dataset:unalignment/spicy-3.1 Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth...   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Bagel DPO 7B V0.1 Benchmarks

Bagel DPO 7B V0.1 Parameters and Internals

LLM NameBagel DPO 7B V0.1
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM14.4 GB
Updated2024-07-27
Maintainerjondurbin
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16
Bagel DPO 7B V0.1 (jondurbin/bagel-dpo-7b-v0.1)

Quantized Models of the Bagel DPO 7B V0.1

Model
Likes
Downloads
VRAM
Bagel DPO 7B V0.1 GGUF64653 GB
Bagel DPO 7B V0.1 AWQ0104 GB
Bagel DPO 7B V0.1 GPTQ074 GB

Best Alternatives to Bagel DPO 7B V0.1

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17020.21024K / 13.5 GB2961
Yarn Llama 2 7B 128K0.2128K / 13.5 GB1274638
LLaMA 7B PoSE YaRN 128K0.2128K / 13.5 GB282
LLaMA 7B PoSE YaRN 96K0.296K / 13.5 GB111
LLaMA 7B PoSE Linear 96K0.296K / 27 GB111
Chat Llama2 7B 80K0.280K / 13.8 GB110
Llama2 7B 80K0.280K / 13.8 GB80
Lloma Step4000.364K / 13.5 GB2940
Lloma Step2000.364K / 13.5 GB2980
Lloma Step500.264K / 13.5 GB2970
Note: green Score (e.g. "73.2") means that the model is better than jondurbin/bagel-dpo-7b-v0.1.

Rank the Bagel DPO 7B V0.1 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 34446 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501