DeciLM 6B Instruct by Deci

 ยป  All LLMs  ยป  Deci  ยป  DeciLM 6B Instruct   URL Share it on

  Autotrain compatible   Custom code Dataset:cerebras/slimpajama-62...   Dataset:open-orca/openorca   Deci ai   Decilm   En   Instruct   Instruction   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Deci/DeciLM-6b-instruct 

DeciLM 6B Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeciLM 6B Instruct (Deci/DeciLM-6b-instruct)

DeciLM 6B Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Considerations:
The model is intended primarily for English but can be fine-tuned for other languages.
Additional Notes 
DeciLM 6B-Instruct has not been aligned for safety or trained using RLHF.
Supported Languages 
English (primary)
Training Details 
Data Sources:
cerebras/SlimPajama-627B, Open-Orca/OpenOrca
Methodology:
LoRA fine-tuning on a subset of the OpenOrca dataset
Model Architecture:
Optimized transformer decoder with variable Grouped-Query Attention.
Input Output 
Input Format:
Encoded text prompts
Accepted Modalities:
text
Output Format:
Text
LLM NameDeciLM 6B Instruct
Repository ๐Ÿค—https://huggingface.co/Deci/DeciLM-6b-instruct 
Model Size6b
Required VRAM11.5 GB
Updated2025-02-22
MaintainerDeci
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   1.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureDeciLMForCausalLM
Licensellama2|other
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to DeciLM 6B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Barcenas 6B4K / 11.5 GB32251
StableGalen 6B4K / 11.5 GB1231
... Hf Open Instruct V1 Blog Post4K / 22.8 GB141
Note: green Score (e.g. "73.2") means that the model is better than Deci/DeciLM-6b-instruct.

Rank the DeciLM 6B Instruct 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