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

Stable Code Instruct 3B by stabilityai

 »  All LLMs  »  stabilityai  »  Stable Code Instruct 3B   URL Share it on

  1906   
  Arxiv:2305.18290   Autotrain compatible   Code   Conversational   En   Endpoints compatible   Gguf   Instruct   Model-index   Q4   Quantized   Region:us   Safetensors   Sharded   Stablelm   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stabilityai/stable-code-instruct-3b 

Stable Code Instruct 3B Benchmarks

LLME Score: 0.23703
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stable Code Instruct 3B (stabilityai/stable-code-instruct-3b)

Stable Code Instruct 3B Parameters and Internals

Model Type 
causal-lm, code
Use Cases 
Areas:
General purpose Code/Software Engineering, SQL related generation and conversation
Primary Use Cases:
Conversations in software development, SQL generation
Additional Notes 
Finetuned from stable-code-3b using DPO method for better performance in code tasks.
Supported Languages 
en (English)
Training Details 
Data Sources:
publicly available datasets, synthetic datasets using Direct Preference Optimization (DPO)
Methodology:
Instruct tuning
Model Architecture:
Transformer decoder architecture
Input Output 
Input Format:
Chat template format
Accepted Modalities:
text
Output Format:
Text completion or code generation
LLM NameStable Code Instruct 3B
Repository 🤗https://huggingface.co/stabilityai/stable-code-instruct-3b 
Model Size3b
Required VRAM5.6 GB
Updated2024-12-22
Maintainerstabilityai
Model Typestablelm
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2   1.7 GB   2.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q4|q4_k|q5_k
Model ArchitectureStableLmForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.38.2
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|endoftext|>
Vocabulary Size50304
Torch Data Typebfloat16

Quantized Models of the Stable Code Instruct 3B

Model
Likes
Downloads
VRAM
Stable Cypher Instruct 3B228291 GB

Best Alternatives to Stable Code Instruct 3B

Best Alternatives
Context / RAM
Downloads
Likes
Stable Cypher Instruct 3B16K / 1.7 GB82922
...struct 3B Spider 1500 Steps Q416K / 1.7 GB150
Stable Code Instruct 3B 4bit16K / 1.8 GB345
...t 3B Mix Spider Bird 200 Steps16K / 5.6 GB110
... Instruct 3B Spider 3500 Steps16K / 11.2 GB100
Stable Code Instruct 3B AWQ16K / 1.8 GB170
Stablelm Zephyr 3B4K / 5.6 GB10181249
ReMask 3B4K / 11.2 GB10615
Note: green Score (e.g. "73.2") means that the model is better than stabilityai/stable-code-instruct-3b.

Rank the Stable Code Instruct 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? 40066 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 v20241217
  Support LLM Explorer