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

Llama 2 7B Dolphin Open Platypus Pruned 70 by neuralmagic

 »  All LLMs  »  neuralmagic  »  Llama 2 7B Dolphin Open Platypus Pruned 70   URL Share it on

  21   
  Arxiv:1905.07830   Arxiv:1907.10641   Arxiv:1911.01547   Arxiv:2009.03300   Arxiv:2109.07958   Arxiv:2110.14168   Arxiv:2405.03594   Autotrain compatible Base model:finetune:neuralmagi... Base model:neuralmagic/llama-2... Dataset:cognitivecomputations/... Dataset:garage-baind/open-plat...   Dataset:open-orca/openorca   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Sparse   Tensorflow
Model Card on HF 🤗: https://huggingface.co/neuralmagic/Llama-2-7b-dolphin-open_platypus-pruned_70 

Llama 2 7B Dolphin Open Platypus Pruned 70 Benchmarks

LLME Score: 0.17192
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Dolphin Open Platypus Pruned 70 (neuralmagic/Llama-2-7b-dolphin-open_platypus-pruned_70)

Llama 2 7B Dolphin Open Platypus Pruned 70 Parameters and Internals

Model Type 
llama
Additional Notes 
The model is finetuned for instruction-following tasks and is 70% sparse, which helps in efficient transfer learning and deployment.
Training Details 
Data Sources:
garage-bAInd/Open-Platypus, Open-Orca/OpenOrca, cognitivecomputations/dolphin
Methodology:
Sparse Transfer
Training Time:
6 epochs
Input Output 
Input Format:
text prompt
Accepted Modalities:
text
Output Format:
Generated text
LLM NameLlama 2 7B Dolphin Open Platypus Pruned 70
Repository 🤗https://huggingface.co/neuralmagic/Llama-2-7b-dolphin-open_platypus-pruned_70 
Base Model(s)  Llama 2 7B Pruned70 Retrained   neuralmagic/Llama-2-7b-pruned70-retrained
Model Size7b
Required VRAM13.5 GB
Updated2025-02-22
Maintainerneuralmagic
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version1.7.0.43401
Tokenizer ClassLlamaTokenizerFast
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Llama 2 7B Dolphin Open Platypus Pruned 70

Best Alternatives
Context / RAM
Downloads
Likes
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB39433
SuperNeuralDreadDevil 8B128K / 16.1 GB541
Falcon3 7B Instruct32K / 14.8 GB4439354
Falcon3 Jessi V0.4 7B Slerp32K / 14.9 GB4869
Jessi V0.4 Falcon3 7B Instruct32K / 14.8 GB790
Jessi V0.6 Falcon3 7B Instruct32K / 14.8 GB340
Taurus Opus 7B32K / 14.8 GB8410
Jessi V0.5 Falcon3 7B Instruct32K / 14.8 GB160
Jessi V0.3 Falcon3 7B Instruct32K / 14.8 GB170
Falcon3 Ultraset32K / 14.8 GB130
Note: green Score (e.g. "73.2") means that the model is better than neuralmagic/Llama-2-7b-dolphin-open_platypus-pruned_70.

Rank the Llama 2 7B Dolphin Open Platypus Pruned 70 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