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 Tulu 2 DPO 70B by allenai

 »  All LLMs  »  allenai  »  Llama 3 Tulu 2 DPO 70B   URL Share it on

  37   
  Arxiv:2305.18290   Arxiv:2311.10702   Autotrain compatible Base model:allenai/llama-3-tul... Base model:finetune:allenai/ll...   Conversational Dataset:allenai/tulu-v2-sft-mi... Dataset:argilla/ultrafeedback-...   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allenai/llama-3-tulu-2-dpo-70b 

Llama 3 Tulu 2 DPO 70B Benchmarks

LLME Score: 0.20108
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Tulu 2 DPO 70B (allenai/llama-3-tulu-2-dpo-70b)

Llama 3 Tulu 2 DPO 70B Parameters and Internals

Model Type 
language model, instruction-following
Use Cases 
Areas:
Research, Commercial applications
Limitations:
Potential to produce problematic outputs, Unknown base data size and composition
Additional Notes 
Trained primarily with English datasets, further aligned with the UltraFeedback dataset using advanced training techniques.
Supported Languages 
English (primary)
Training Details 
Data Sources:
allenai/tulu-v2-sft-mixture, argilla/ultrafeedback-binarized-preferences-cleaned
Data Volume:
Unknown
Methodology:
Mixture of publicly available, synthetic, and human datasets; DPO training with Jax DPO trainer and EasyLM on the UltraFeedback dataset.
Model Architecture:
Enhanced adaptation with Tulu 2
Responsible Ai Considerations 
Mitigation Strategies:
No specific RLHF phase or in-the-loop response filtering like ChatGPT. Potential for problematic outputs.
Input Output 
Input Format:
<|user|> Your message here! <|assistant|>
Accepted Modalities:
text
Performance Tips:
Include a newline after <|assistant|> for improved generation quality.
LLM NameLlama 3 Tulu 2 DPO 70B
Repository 🤗https://huggingface.co/allenai/llama-3-tulu-2-dpo-70b 
Base Model(s)  Llama 3 Tulu 2 70B   allenai/llama-3-tulu-2-70b
Model Size70b
Required VRAM141.9 GB
Updated2025-01-24
Maintainerallenai
Model Typellama
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
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<s>
End of Sentence Token</s>
Padding Token<pad>
Unk Token<unk>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 Tulu 2 DPO 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB32825
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB359121
Llama3 Function Calling 1048K1024K / 141.9 GB211
...a 3 70B Instruct Gradient 524K512K / 141.9 GB6623
...a 3 70B Instruct Gradient 262K256K / 141.9 GB7955
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB373
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB180
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB232
Yi 70B 200K RPMerge Franken195K / 142.4 GB101
DeepSeek R1 Distill Llama 70B128K / 141 GB10506198
Note: green Score (e.g. "73.2") means that the model is better than allenai/llama-3-tulu-2-dpo-70b.

Rank the Llama 3 Tulu 2 DPO 70B 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? 41817 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