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

DeciLM 7B Instruct by Deci

 »  All LLMs  »  Deci  »  DeciLM 7B Instruct   URL Share it on

  2623   
  Autotrain compatible   Conversational   Custom code   Dataset:open-orca/slimorca   Deci   En   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Deci/DeciLM-7B-instruct 

DeciLM 7B Instruct Benchmarks

MMLU Pro: 17.87
GPQA: 5.26
MUSR: 5.99
BBH: 23.89
IFEval: 48.8 vs 88 (so35)-44.5%
ARC: 61.01 vs 96.7 (so35)-36.9%
HellaSwag: 82.37 vs 95.3 (gpt4)-13.6%
MMLU: 60.24 vs 88.3 (so35)-31.8%
TruthfulQA: 49.75 vs 59 (gpt4)-15.7%
WinoGrande: 79.72 vs 87.5 (gpt4)-8.9%
GSM8K: 46.02 vs 96.4 (so35)-52.3%
MATH Lvl 5: 3.02
LLME Score: 0.21981
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeciLM 7B Instruct (Deci/DeciLM-7B-instruct)
🌟 Advertise your project 🚀

DeciLM 7B Instruct Parameters and Internals

Model Type 
auto-regressive language model
Use Cases 
Areas:
commercial, research
Limitations:
It may produce inaccurate, biased, or otherwise objectionable outputs
Considerations:
Thorough safety testing and tuning is recommended before deployment.
Supported Languages 
English (high)
Training Details 
Data Sources:
Open-Orca/SlimOrca
Methodology:
LoRA fine-tuning
Context Length:
8192
Model Architecture:
Optimized transformer decoder architecture using variable Grouped-Query Attention
Safety Evaluation 
Ethical Considerations:
DeciLM-7B's outputs may be unpredictable, and the model may generate responses that are inaccurate, biased, or objectionable.
Input Output 
Input Format:
System: {system_prompt} User: {user_prompt} Assistant:
Accepted Modalities:
text
Output Format:
Generated text
LLM NameDeciLM 7B Instruct
Repository 🤗https://huggingface.co/Deci/DeciLM-7B-instruct 
Model Size7b
Required VRAM14.1 GB
Updated2025-09-23
MaintainerDeci
Model Typedeci
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   4.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureDeciLMForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the DeciLM 7B Instruct

Model
Likes
Downloads
VRAM
DeciLM 7B Instruct GGUF391227 GB

Best Alternatives to DeciLM 7B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
DeciLM 7B Instruct 128K128K / 14.1 GB53
DeciLM 7B Instruct 32K32K / 14.1 GB63
DeciLM 7B Instruct GGUF8K / 7.5 GB12239
...B Instruct Gptq 4bit Slim Orca8K / 4.1 GB91
...B Instruct Gptq 2bit Slim Orca8K / 2.4 GB81

Rank the DeciLM 7B Instruct 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? 51544 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 v20241124
  Support LLM Explorer