Codegen 2B Multi by Salesforce

 ยป  All LLMs  ยป  Salesforce  ยป  Codegen 2B Multi   URL Share it on

  Arxiv:2203.13474   Autotrain compatible   Codegen   Endpoints compatible   Pytorch   Region:us

Codegen 2B Multi Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codegen 2B Multi (Salesforce/codegen-2B-multi)

Codegen 2B Multi Parameters and Internals

Model Type 
text generation, program synthesis
Use Cases 
Areas:
research, commercial applications
Applications:
program synthesis, code generation
Primary Use Cases:
Generating executable code from English prompts, Completing partially generated code
Limitations:
Only best at program synthesis tasks
Considerations:
Prompts should be in the form of a comment string
Supported Languages 
Python (High), C (High), C++ (High), Go (High), Java (High), JavaScript (High)
Training Details 
Data Sources:
BigQuery, GitHub repositories
Data Volume:
119.2B tokens
Methodology:
Cross-entropy loss to maximize likelihood of sequential inputs
Hardware Used:
TPU-v4-512
Model Architecture:
Autoregressive language model
LLM NameCodegen 2B Multi
Repository ๐Ÿค—https://huggingface.co/Salesforce/codegen-2B-multi 
Model Size2b
Required VRAM5.7 GB
Updated2025-02-22
MaintainerSalesforce
Model Typecodegen
Model Files  5.7 GB
Generates CodeYes
Model ArchitectureCodeGenForCausalLM
Licensebsd-3-clause
Model Max Length2048
Transformers Version4.21.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size51200
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to Codegen 2B Multi

Best Alternatives
Context / RAM
Downloads
Likes
...Python 18K Alpaca Full Dataset0K / 5.6 GB1070
Archgen 2B V10K / 5.6 GB80
Salesforce Codegen 2B Multi Ov0K / 11.1 GB90
Nsql 2B0K / 11.3 GB879
Instruct Codegen 2B Multi0K / 11.3 GB131
Diff Codegen 2B V20K / 5.7 GB446
...en 2B Mono Instruct Py Revised0K / 11.3 GB21
Codegen 2B Mono Xlcost0K / 5.7 GB131
Codegen 2B Multi Xlcost0K / 5.7 GB1081
Fine Tuned Codegen 2B Verilog0K / 11.3 GB2577
Note: green Score (e.g. "73.2") means that the model is better than Salesforce/codegen-2B-multi.

Rank the Codegen 2B Multi 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