Llama3 8B DPO by CultriX

 ยป  All LLMs  ยป  CultriX  ยป  Llama3 8B DPO   URL Share it on

Base model:finetune:nousresear... Base model:nousresearch/hermes... Dataset:cultrix/llama70b-dpo-d...   Dpo   En   Endpoints compatible   General   Llama3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/CultriX/Llama3-8B-DPO 

Llama3 8B DPO Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Llama3 8B DPO Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (fluent)
Training Details 
Data Sources:
CultriX/llama70B-dpo-dataset
Methodology:
The model is fine-tuned using LoRA (Low-Rank Adaptation) and DPO (Dialogue Pre-Trained Optimization) configuration.
Context Length:
4096
Training Time:
4 epochs
Model Architecture:
Hermes-3-Llama-3.1-8B with LoRA adjustments
LLM NameLlama3 8B DPO
Repository ๐Ÿค—https://huggingface.co/CultriX/Llama3-8B-DPO 
Base Model(s)  NousResearch/Hermes-3-Llama-3.1-8B   NousResearch/Hermes-3-Llama-3.1-8B
Model Size8b
Required VRAM16.1 GB
Updated2025-03-01
MaintainerCultriX
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 Length131072
Model Max Length131072
Transformers Version4.46.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|im_end|>
Vocabulary Size128256
Torch Data Typebfloat16
Llama3 8B DPO (CultriX/Llama3-8B-DPO)

Best Alternatives to Llama3 8B DPO

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3395108
UltraLong Thinking4192K / 16.1 GB5072
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB62215
Zero Llama 3.1 8B Beta61048K / 16.1 GB10941
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB175445
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB634
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB932
Note: green Score (e.g. "73.2") means that the model is better than CultriX/Llama3-8B-DPO.

Rank the Llama3 8B DPO 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? 48075 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124