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 8B Orpo V0.1 by dfurman

 »  All LLMs  »  dfurman  »  Llama 3 8B Orpo V0.1   URL Share it on

  5015   
  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational Dataset:mlabonne/orpo-dpo-mix-...   En   Endpoints compatible   Llama   Llama 3   Model-index   Orpo   Region:us   Rlhf   Safetensors   Sft   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dfurman/Llama-3-8B-Orpo-v0.1 

Llama 3 8B Orpo V0.1 Benchmarks

MMLU Pro: 14.23
GPQA: 1.57
MUSR: 2.73
BBH: 13.77
IFEval: 30 vs 88 (so35)-65.9%
ARC: 60.67 vs 96.7 (so35)-37.3%
HellaSwag: 82.56 vs 95.3 (gpt4)-13.4%
MMLU: 66.59 vs 88.3 (so35)-24.6%
TruthfulQA: 50.47 vs 59 (gpt4)-14.5%
WinoGrande: 79.01 vs 87.5 (gpt4)-9.7%
GSM8K: 48.75 vs 96.4 (so35)-49.4%
MATH Lvl 5: 4.15
LLME Score: 0.27656
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Orpo V0.1 (dfurman/Llama-3-8B-Orpo-v0.1)

Llama 3 8B Orpo V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
The model is an ORPO fine-tune with improved performance in certain benchmark scores as compared to its base model.
Training Details 
Data Sources:
mlabonne/orpo-dpo-mix-40k
Data Volume:
4k samples
Methodology:
Fine-tuning with the ChatML template
Context Length:
8000
LLM NameLlama 3 8B Orpo V0.1
Repository 🤗https://huggingface.co/dfurman/Llama-3-8B-Orpo-v0.1 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM16.1 GB
Updated2025-01-23
Maintainerdfurman
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
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|im_end|>
Vocabulary Size128258
Torch Data Typefloat16

Best Alternatives to Llama 3 8B Orpo V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB6585680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
Because Im Bored Nsfw11024K / 16.1 GB431
41024K / 16.1 GB3220
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
161024K / 16.1 GB1690
111024K / 16.1 GB1130
NBeerbower Narrative 8B 64K1024K / 16.1 GB141
HEL V0.8 8B LONG DARK1024K / 16.1 GB2320
Note: green Score (e.g. "73.2") means that the model is better than dfurman/Llama-3-8B-Orpo-v0.1.

Rank the Llama 3 8B Orpo V0.1 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? 41774 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 v20241227
  Support LLM Explorer