Llama 3 8B Sft Mixture by OpenLLMAI

 ยป  All LLMs  ยป  OpenLLMAI  ยป  Llama 3 8B Sft Mixture   URL Share it on

  Arxiv:2405.07863   Autotrain compatible   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Llama 3 8B Sft Mixture 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€

Llama 3 8B Sft Mixture Parameters and Internals

Model Type 
SFT, text generation
Use Cases 
Considerations:
The model is a good starting point for RLHF research.
Training Details 
Data Sources:
ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract
Methodology:
Trained for 1 epoch on a mixture of diverse open-source high-quality datasets with detailed parameters specified in the report.
Model Architecture:
Derived from Meta-Llama-3-8B
Release Notes 
Version:
Latest
Notes:
Fixed generation_config.json. Intended for use in Online-RLHF project, without RLHF training.
LLM NameLlama 3 8B Sft Mixture
Repository ๐Ÿค—https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture 
Model Size8b
Required VRAM16.1 GB
Updated2025-06-09
MaintainerOpenLLMAI
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
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16
Llama 3 8B Sft Mixture (OpenRLHF/Llama-3-8b-sft-mixture)

Best Alternatives to Llama 3 8B Sft Mixture

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3284108
UltraLong Thinking4192K / 16.1 GB3672
...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 GB52615
Zero Llama 3.1 8B Beta61048K / 16.1 GB9581
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB180845
...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 GB902
Note: green Score (e.g. "73.2") means that the model is better than OpenRLHF/Llama-3-8b-sft-mixture.

Rank the Llama 3 8B Sft Mixture 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? 48046 in total.

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