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 70B Instruct DPO V0.4 by MaziyarPanahi

 »  All LLMs  »  MaziyarPanahi  »  Llama 3 70B Instruct DPO V0.4   URL Share it on

  361   
  Autotrain compatible   Axolotl Base model:meta-llama/meta-lla...   Chatml   Conversational Dataset:argilla/ultrafeedback-...   Dpo   En   Facebook   Finetuned   Instruct   License:llama3   Llama   Llama-3   Meta   Model-index   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4 

Llama 3 70B Instruct DPO V0.4 Benchmarks

MMLU Pro: 46.71
GPQA: 11.97
MUSR: 13.1
BBH: 48.4
IFEval: 50.27 vs 88 (so35)-42.9%
ARC: 72.61 vs 96.7 (so35)-24.9%
HellaSwag: 86.03 vs 95.3 (gpt4)-9.7%
MMLU: 80.5 vs 88.3 (so35)-8.8%
TruthfulQA: 63.26 vs 59 (gpt4)7.2%
WinoGrande: 83.58 vs 87.5 (gpt4)-4.5%
GSM8K: 87.34 vs 96.4 (so35)-9.4%
MATH Lvl 5: 22.66
LLME Score: 0.30156
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 70B Instruct DPO V0.4 (MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4)

Llama 3 70B Instruct DPO V0.4 Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is a fine-tuned version using the DPO method and is optimized for text generation tasks.
Input Output 
Input Format:
ChatML prompt template
Accepted Modalities:
text
Output Format:
Generated text based on input prompts
LLM NameLlama 3 70B Instruct DPO V0.4
Repository 🤗https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4 
Model CreatorMaziyarPanahi
Base Model(s)  Meta Llama 3 70B Instruct   meta-llama/Meta-Llama-3-70B-Instruct
Model Size70b
Required VRAM141.9 GB
Updated2024-07-20
MaintainerMaziyarPanahi
Model Typellama
Instruction-BasedYes
Model Files  4.6 GB: 1-of-30   4.7 GB: 2-of-30   5.0 GB: 3-of-30   5.0 GB: 4-of-30   4.7 GB: 5-of-30   4.7 GB: 6-of-30   4.7 GB: 7-of-30   5.0 GB: 8-of-30   5.0 GB: 9-of-30   4.7 GB: 10-of-30   4.7 GB: 11-of-30   4.7 GB: 12-of-30   5.0 GB: 13-of-30   5.0 GB: 14-of-30   4.7 GB: 15-of-30   4.7 GB: 16-of-30   4.7 GB: 17-of-30   5.0 GB: 18-of-30   5.0 GB: 19-of-30   4.7 GB: 20-of-30   4.7 GB: 21-of-30   4.7 GB: 22-of-30   5.0 GB: 23-of-30   5.0 GB: 24-of-30   4.7 GB: 25-of-30   4.7 GB: 26-of-30   4.7 GB: 27-of-30   5.0 GB: 28-of-30   5.0 GB: 29-of-30   2.1 GB: 30-of-30
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to Llama 3 70B Instruct DPO V0.4

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB31355
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB248121
Llama3 Function Calling 1048K1024K / 141.9 GB41
...a 3 70B Instruct Gradient 524K512K / 141.9 GB4323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB17355
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB393
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB170
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB312
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB1773771937
Meta Llama 3.1 70B Instruct128K / 141.9 GB521937513
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4.

Rank the Llama 3 70B Instruct DPO V0.4 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? 40248 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 v20241217
  Support LLM Explorer