Evol Replit V1 by nickrosh

 ยป  All LLMs  ยป  nickrosh  ยป  Evol Replit V1   URL Share it on

  Autotrain compatible   Custom code Dataset:nickrosh/evol-instruct...   Endpoints compatible   Instruct   Mpt   Pytorch   Region:us   Sharded
Model Card on HF ๐Ÿค—: https://huggingface.co/nickrosh/Evol-Replit-v1 

Evol Replit V1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Evol Replit V1 (nickrosh/Evol-Replit-v1)

Evol Replit V1 Parameters and Internals

Model Type 
Code Generation
Additional Notes 
Currently, WizardCoder is one the most performant Code Generation models, being beaten only by ChatGPT.
Training Details 
Data Sources:
Evol-Instruct-Code-80k-v1
Context Length:
2000
LLM NameEvol Replit V1
Repository ๐Ÿค—https://huggingface.co/nickrosh/Evol-Replit-v1 
Model Size3b
Required VRAM10.4 GB
Updated2025-02-22
Maintainernickrosh
Model Typempt
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   0.4 GB: 2-of-2   0.0 GB
Model ArchitectureMPTForCausalLM
Licensecc-by-sa-4.0
Model Max Length2000
Transformers Version4.30.2
Tokenizer ClassReplitLMTokenizer
Padding Token<|pad|>
Vocabulary Size32768
Torch Data Typefloat32

Best Alternatives to Evol Replit V1

Best Alternatives
Context / RAM
Downloads
Likes
Mpt 3B 8K Instruct0K / 6.9 GB43
Note: green Score (e.g. "73.2") means that the model is better than nickrosh/Evol-Replit-v1.

Rank the Evol Replit V1 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? 43470 in total.

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