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

Dolphin 2.2 70B by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.2 70B   URL Share it on

  149   
  Merged Model   Autotrain compatible   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2....   En   Endpoints compatible   Instruct   Llama   Model-index   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.2-70b 

Dolphin 2.2 70B Benchmarks

LLME Score: 0.14949
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.2 70B (cognitivecomputations/dolphin-2.2-70b)

Dolphin 2.2 70B Parameters and Internals

Model Type 
text generation
Use Cases 
Limitations:
Highly compliant to any requests, including unethical ones
Considerations:
Implement alignment layer before exposing model as a service.
Additional Notes 
Trained with a concentration on conversation and empathy, includes curated Samantha and WizardLM data.
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/samantha-data, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
Methodology:
Trained for uncensoring, creativity, and long multi-turn conversation using qLoRA and Axolotl.framework with ChatML prompt format.
Training Time:
5 days
Hardware Used:
4x A100s
Safety Evaluation 
Risk Categories:
Risk of unethical responses due to uncensored state
Ethical Considerations:
Highly compliant even to unethical requests.
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
Text generation
LLM NameDolphin 2.2 70B
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.2-70b 
Merged ModelYes
Model Size70b
Required VRAM138 GB
Updated2025-02-22
Maintainercognitivecomputations
Model Typellama
Instruction-BasedYes
Model Files  9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15   9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Dolphin 2.2 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB25245
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB199121
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18655
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB3212
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB653
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB120
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB1223352021
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.2-70b.

Rank the Dolphin 2.2 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? 43470 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