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

Stablecode Completion Alpha 3B by stabilityai

 »  All LLMs  »  stabilityai  »  Stablecode Completion Alpha 3B   URL Share it on

  120   
  Arxiv:1910.02054   Arxiv:2104.09864   Autotrain compatible   Code   Codegen   Dataset:bigcode/starcoderdata   Endpoints compatible   Gpt neox   Model-index   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/stabilityai/stablecode-completion-alpha-3b 

Stablecode Completion Alpha 3B Benchmarks

HumanEvalA: 8.1
Python Eva: 20.2 vs 92 (so35)-78%
Java Eval: 19.54
Javascript: 18.98
CPP Eval: 20.77
PHP Eval: 3.95
D Eval: 4.77
Lua Eval: 5.14
R Eval: 0.8
Racket Eva: 0.008
Rust Eval: 2.03
Swift Eval: 0.98
LLME Score: 0.13103
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stablecode Completion Alpha 3B (stabilityai/stablecode-completion-alpha-3b)

Stablecode Completion Alpha 3B Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
code generation
Applications:
single/multiline code completion in multiple programming languages
Primary Use Cases:
code completion from a long context window
Limitations:
Not intended to create unlawful content or engage in activities with high risk of harm.
Additional Notes 
The model uses the StarCoder tokenizer with a vocabulary size of 49,000.
Supported Languages 
Code (supported)
Training Details 
Data Sources:
bigcode/starcoderdata
Data Volume:
300B tokens for pre-training, additional 200B for fine-tuning
Methodology:
Pre-trained using a multi-stage context length extension schedule, first pre-training at a context length of 4096 tokens, then fine-tuning at 16384 tokens.
Context Length:
16384
Model Architecture:
Decoder-only transformer with parallel attention and MLP residuals, single input LayerNorm, rotary position embeddings, LayerNorm bias terms only.
Input Output 
Input Format:
Code (programming language syntax)
Accepted Modalities:
text
Output Format:
Code
LLM NameStablecode Completion Alpha 3B
Repository 🤗https://huggingface.co/stabilityai/stablecode-completion-alpha-3b 
Model Size3b
Required VRAM14.1 GB
Updated2025-02-05
Maintainerstabilityai
Model Typegpt_neox
Model Files  14.1 GB
Supported Languagescode
Generates CodeYes
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.29.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size49152
Torch Data Typefloat16

Best Alternatives to Stablecode Completion Alpha 3B

Best Alternatives
Context / RAM
Downloads
Likes
...blecode Completion Alpha 3B 4K4K / 6.1 GB1436282
Stablecode Instruct Alpha 3B4K / 6.1 GB35304
StableCode 3B4K / 6.1 GB141
...tion Alpha 3B 4K Openvino Int84K / 2.8 GB231
...blecode Instruct Alpha 3B GPTQ4K / 1.8 GB1717
...de Completion Alpha 3B 4K GPTQ4K / 1.8 GB229
...blecode Instruct Alpha 3B GPTQ4K / 1.8 GB61
Note: green Score (e.g. "73.2") means that the model is better than stabilityai/stablecode-completion-alpha-3b.

Rank the Stablecode Completion Alpha 3B 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? 42577 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