Opt Peter 2.7B by pszemraj

 ยป  All LLMs  ยป  pszemraj  ยป  Opt Peter 2.7B   URL Share it on

  Ai-msgbot   Autotrain compatible   Base model:facebook/opt-2.7b Base model:finetune:facebook/o...   Chatbot   Dialogue   Doi:10.57967/hf/0233   Endpoints compatible   Generated from trainer   Non-commercial   Opt   Pytorch   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/pszemraj/opt-peter-2.7B 

Opt Peter 2.7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opt Peter 2.7B (pszemraj/opt-peter-2.7B)

Opt Peter 2.7B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
non-commercial
Applications:
dialogue, conversational applications, chatbot
Primary Use Cases:
text generation
Limitations:
Model is too large for API use, require high RAM
Considerations:
Use responsibly, as it is a fine-tuned version of the base model.
Additional Notes 
Sharded checkpoint available due to large size of model file.
Training Details 
Data Sources:
WhatsApp text messages, iMessages
Data Volume:
about 80k messages
Methodology:
Fine-tuning
LLM NameOpt Peter 2.7B
Repository ๐Ÿค—https://huggingface.co/pszemraj/opt-peter-2.7B 
Base Model(s)  facebook/opt-2.7b   facebook/opt-2.7b
Model Size2.7b
Required VRAM10.6 GB
Updated2025-04-30
Maintainerpszemraj
Model Typeopt
Model Files  10.6 GB   10.6 GB   0.0 GB
Model ArchitectureOPTForCausalLM
Licenseother|apache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.19.2
Beginning of Sentence Token</s>
End of Sentence Token</s>
Unk Token</s>
Vocabulary Size50265
Torch Data Typefloat32
Activation Functionrelu
Errorsreplace

Best Alternatives to Opt Peter 2.7B

Best Alternatives
Context / RAM
Downloads
Likes
LLmRa 2.7B2K / 10.6 GB6421
OPT 2.7B Nerybus Mix2K / 5.5 GB39610
Opt 2.7B2K / 5.3 GB5587483
OPT 2.7B Erebus2K / 5.3 GB429441
Opt 2.7B Realtime Chat V22K / 11.1 GB50
LongForm OPT 2.7B2K / 5.3 GB153
Opt 2.7B Wikitext22K / 11.1 GB50
OPT 2.7B Nerys V22K / 5.3 GB406
Opt 2.7B Realtime Chat2K / 11.1 GB52
Opt 2.7B AWQ2K / 1.6 GB120
Note: green Score (e.g. "73.2") means that the model is better than pszemraj/opt-peter-2.7B.

Rank the Opt Peter 2.7B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 46860 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227