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

Llama 3 Instruct 8B SPPO Iter3 by UCLA-AGI

 »  All LLMs  »  UCLA-AGI  »  Llama 3 Instruct 8B SPPO Iter3   URL Share it on

  6817   
  Arxiv:2405.00675   Autotrain compatible   Conversational   Dataset:openbmb/ultrafeedback   En   Endpoints compatible   Instruct   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow

Llama 3 Instruct 8B SPPO Iter3 Benchmarks

MMLU Pro: 29.53
GPQA: 2.01
MUSR: 2.89
BBH: 29.72
IFEval: 67.03 vs 88 (so35)-23.8%
MATH Lvl 5: 7.18
LLME Score: 0.36699
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 3 Instruct 8B SPPO Iter3 Parameters and Internals

Model Type
GPT-like model, fine-tuned on synthetic datasets
Supported Languages
Primary Language (English), Proficiency ()
Training Details
Data Sources:
openbmb/UltraFeedback, snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
Methodology:Self-Play Preference Optimization at iteration 3
Hardware Used:
8 devices
Model Architecture:Based on Meta-Llama-3-8B-Instruct architecture
LLM NameLlama 3 Instruct 8B SPPO Iter3
Repository 🤗https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 
Model Size8b
Required VRAM16.1 GB
Updated2024-11-12
MaintainerUCLA-AGI
Model Typellama
Instruction-BasedYes
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<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16
Llama 3 Instruct 8B SPPO Iter3 (UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3)

Quantized Models of the Llama 3 Instruct 8B SPPO Iter3

Model
Likes
Downloads
VRAM
...struct 8B SPPO Iter3 Bpw4 EXL2075 GB

Best Alternatives to Llama 3 Instruct 8B SPPO Iter3

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB12810672
L3.1 Gradient1024K / 16.1 GB100
...SLERP Gradient1048k OpenBioLLM1024K / 16.1 GB160
...lama3 8B Special Dark V3.1.2aa1024K / 16.1 GB130
Llama3 8B Special Dark V3.1.2B1024K / 16.1 GB120
...lama3 8B Special Dark V3.1.1yy1024K / 16.1 GB140
Loki1024K / 16.1 GB90
Unholy Thoth 8B V21024K / 16.1 GB120
...struct Gradient 1048K MAC Lora1024K / 5.9 GB142
... Instruct Gradient 1048K Agent1024K / 16.1 GB621
Note: green Score (e.g. "73.2") means that the model is better than UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3.

Rank the Llama 3 Instruct 8B SPPO Iter3 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? 37901 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 v20241110
  Support LLM Explorer