DPO 3 10K by ksw1

 ยป  All LLMs  ยป  ksw1  ยป  DPO 3 10K   URL Share it on

  Autotrain compatible Base model:finetune:ksw1/llama... Base model:ksw1/llama-3-8b-sle...   Conversational   Dpo   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth

DPO 3 10K Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

DPO 3 10K Parameters and Internals

LLM NameDPO 3 10K
Repository ๐Ÿค—https://huggingface.co/ksw1/DPO-3-10k 
Base Model(s)  Llama 3 8B Sleeper Agent   ksw1/llama-3-8b-sleeper-agent
Model Size8b
Required VRAM16.1 GB
Updated2024-09-06
Maintainerksw1
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
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16
DPO 3 10K (ksw1/DPO-3-10k)

Best Alternatives to DPO 3 10K

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB16769662
...struct Gradient 1048K MAC Lora1024K / 5.9 GB133402
Loki V2.11024K / 16.1 GB120
Llama3 8B Special Dark RP21024K / 16.1 GB121
...SLERP Gradient1048k OpenBioLLM1024K / 16.1 GB80
Llama3 8B Special Dark V3.1.2a1024K / 16.1 GB120
Llama3 8B Special Dark V3.1.1t1024K / 16.1 GB130
Llama3 8B Special Dark RP11024K / 16.1 GB120
Llama3 8B Special Dark V3.1.2c1024K / 16.1 GB71
Llama3 8B Special Dark V3.1.2B1024K / 16.1 GB90
Note: green Score (e.g. "73.2") means that the model is better than ksw1/DPO-3-10k.

Rank the DPO 3 10K 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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803