Bigcode Starcoder2 3B 8bits by RichardErkhov

 ยป  All LLMs  ยป  RichardErkhov  ยป  Bigcode Starcoder2 3B 8bits   URL Share it on

  Arxiv:2004.05150   Arxiv:2205.14135   Arxiv:2207.14255   Arxiv:2305.13245   Arxiv:2402.19173   8-bit   Autotrain compatible   Bitsandbytes   Code   Endpoints compatible   Region:us   Safetensors   Starcoder2

Bigcode Starcoder2 3B 8bits Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bigcode Starcoder2 3B 8bits (RichardErkhov/bigcode_-_starcoder2-3b-8bits)

Bigcode Starcoder2 3B 8bits Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Limitations:
Does not work well with commands like 'Write a function that computes the square root.', Generated code may be inefficient, contain bugs, or exploits.
Additional Notes 
Pretraining dataset filtered for permissive licenses and code with no license.
Training Details 
Data Sources:
GitHub, Arxiv, Wikipedia
Data Volume:
3+ trillion tokens
Methodology:
Fill-in-the-Middle objective
Context Length:
16384
Hardware Used:
160 A100 GPUs
Model Architecture:
Transformer decoder with grouped-query and sliding window attention
Input Output 
Output Format:
text
LLM NameBigcode Starcoder2 3B 8bits
Repository ๐Ÿค—https://huggingface.co/RichardErkhov/bigcode_-_starcoder2-3b-8bits 
Model Size3b
Required VRAM3.2 GB
Updated2025-01-30
MaintainerRichardErkhov
Model Typestarcoder2
Model Files  3.2 GB
Model ArchitectureStarcoder2ForCausalLM
Licensebigcode-openrail-m
Context Length16384
Model Max Length16384
Transformers Version4.39.3
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typefloat16

Best Alternatives to Bigcode Starcoder2 3B 8bits

Best Alternatives
Context / RAM
Downloads
Likes
Starcoder2 3B16K / 12.1 GB552570159
Starcoder2 3b AutoRedteam16K / 12.7 GB210
Starcoder Proto Code16K / 6.1 GB60
Mojo Starcoder216K / 6.4 GB110
NEARCoder 3B16K / 6.1 GB1340
NEAR PreTrainedStarCoder216K / 6.1 GB1140
NEAR StructTunedStarcoder216K / 6.1 GB790
Starcoder2 3B Instruct16K / 6.1 GB723
Opencsg Starcoder2 3B V0.116K / 6.4 GB911
OpenCodeInterpreter SC2 3B16K / 6.4 GB77
Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/bigcode_-_starcoder2-3b-8bits.

Rank the Bigcode Starcoder2 3B 8bits 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? 42577 in total.

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