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

Tulu 2 DPO 70B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Tulu 2 DPO 70B GPTQ   URL Share it on

  23   
  Arxiv:2305.18290   Arxiv:2311.10702   4-bit   Autotrain compatible Base model:allenai/tulu-2-dpo-... Base model:quantized:allenai/t... Dataset:allenai/tulu-v2-sft-mi... Dataset:huggingfaceh4/ultrafee...   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/tulu-2-dpo-70B-GPTQ 

Tulu 2 DPO 70B GPTQ Benchmarks

LLME Score: 0.14862
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tulu 2 DPO 70B GPTQ (TheBloke/tulu-2-dpo-70B-GPTQ)

Tulu 2 DPO 70B GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Limitations:
The model can produce problematic outputs when prompted to do so.
Considerations:
Model not aligned for safe completions like ChatGPT.
Additional Notes 
Model files and permutations available for different quantisation settings.
Supported Languages 
en (primary)
Training Details 
Data Sources:
HuggingFaceH4/ultrafeedback_binarized, allenai/tulu-v2-sft-mixture
Methodology:
Direct Preference Optimization (DPO)
Model Architecture:
Llama 2 fine-tuned with DPO
Input Output 
Input Format:
<|user|> {prompt} <|assistant|>
Performance Tips:
Ensure newlines are used as expected for best generation quality.
LLM NameTulu 2 DPO 70B GPTQ
Repository 🤗https://huggingface.co/TheBloke/tulu-2-dpo-70B-GPTQ 
Model NameTulu 2 DPO 70B
Model CreatorAllen Institute for AI
Base Model(s)  Tulu 2 DPO 70B   allenai/tulu-2-dpo-70b
Model Size70b
Required VRAM35.3 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  35.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Tulu 2 DPO 70B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB60266
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB18171
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB204
Opus V1.2 70B Marlin32K / 36.4 GB50
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB221
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB211
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB8122
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB3063
Miqu 1 70B Sf GPTQ31K / 36.7 GB7239
Tess 70B V1.6 Marlin31K / 36.3 GB71
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/tulu-2-dpo-70B-GPTQ.

Rank the Tulu 2 DPO 70B GPTQ 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? 42565 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