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

Dolphin Llama2 7B by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin Llama2 7B   URL Share it on

  25   

Dolphin Llama2 7B is an open-source language model by cognitivecomputations. Features: 7b LLM, VRAM: 13.5GB, Context: 4K, License: llama2, LLM Explorer Score: 0.09.

  Autotrain compatible   Dataset:ehartford/dolphin   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-llama2-7b 

Dolphin Llama2 7B Benchmarks

LLME Score: 0.09282
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin Llama2 7B (cognitivecomputations/dolphin-llama2-7b)
🌟 Advertise your project 🚀

Dolphin Llama2 7B Parameters and Internals

Model Type 
text generation
Additional Notes 
Detailed example outputs and system prompts provided in the model description.
Supported Languages 
en (English)
Training Details 
Data Sources:
Microsoft's Orca
Data Volume:
842,610 instructions of FLANv2 with GPT-4 completions and 2,625,353 instructions of FLANv2 with GPT-3.5 completions
Methodology:
Training followed submix and system prompt distribution with filters for uncensoring and cleaning. Used flan5m and flan1m datasets for different epochs.
Training Time:
400 hours
Hardware Used:
8x A100 GPUs
Responsible Ai Considerations 
Fairness:
Dataset filtered to remove alignment and bias, requiring an additional alignment layer for ethical use.
Accountability:
Users are accountable for content generated using the model.
Input Output 
Input Format:
Prompt format similar to Vicuna with additional SYSTEM field.
Accepted Modalities:
text
Output Format:
Text response based on detailed prompts.
Performance Tips:
Layer personalized alignment LoRA for safe deployment.
LLM NameDolphin Llama2 7B
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-llama2-7b 
Model Size7b
Required VRAM13.5 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Dolphin Llama2 7B

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
1621024K / 16.1 GB600
1571024K / 16.1 GB1010
1181024K / 16.1 GB150
A5.41024K / 16.1 GB120
A6 L1024K / 16.1 GB2010
A3.41024K / 16.1 GB130
A2.41024K / 16.1 GB120
M1024K / 16.1 GB1270
2 Very Sci Fi1024K / 16.1 GB3170
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-llama2-7b.

Rank the Dolphin Llama2 7B 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer