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

Damysus 2.7B Chat by prince-canuma

 »  All LLMs  »  prince-canuma  »  Damysus 2.7B Chat   URL Share it on

  57   
  Autotrain compatible Base model:finetune:microsoft/...   Base model:microsoft/phi-2   Conversational   Custom code   Dataset:open-orca/slimorca   Dataset:prince-canuma/tinyorca   En   Endpoints compatible   Instruct   Model-index   Phi   Phi-2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/prince-canuma/Damysus-2.7B-Chat 

Damysus 2.7B Chat Benchmarks

ARC: 59.13 vs 96.7 (so35)-38.9%
HellaSwag: 74.36 vs 95.3 (gpt4)-22%
MMLU: 56.34 vs 88.3 (so35)-36.2%
TruthfulQA: 46.45 vs 59 (gpt4)-21.3%
WinoGrande: 75.06 vs 87.5 (gpt4)-14.2%
GSM8K: 50.19 vs 96.4 (so35)-47.9%
LLME Score: 0.18542
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Damysus 2.7B Chat (prince-canuma/Damysus-2.7B-Chat)

Damysus 2.7B Chat Parameters and Internals

Model Type 
Transformer, Instruction-tuned
Use Cases 
Areas:
NLP, Instruction following
Applications:
Text generation, Data extraction, Structured outputs, Q&A, Explanations
Primary Use Cases:
Answer synthesizer, Summarizer, Query rewriter
Limitations:
May generate inaccurate code, Limited code scope, particularly outside Python, Designed primarily for standard English
Considerations:
Users are advised to verify outputs for accuracy, especially in technical domains.
Additional Notes 
Optimal performance derived from fine-tuning on smaller, curated datasets. Recommended for use in structured output tasks and conversational queries.
Supported Languages 
en (primary)
Training Details 
Data Sources:
Open-Orca/SlimOrca, prince-canuma/TinyOrca
Methodology:
Instruction-tuned with additional training to better follow user instructions. Fine-tuned on a subset of Open-Orca data.
Context Length:
2048
Model Architecture:
Transformer
LLM NameDamysus 2.7B Chat
Repository 🤗https://huggingface.co/prince-canuma/Damysus-2.7B-Chat 
Base Model(s)  Phi 2   microsoft/phi-2
Model Size2.7b
Required VRAM11.1 GB
Updated2025-02-22
Maintainerprince-canuma
Model Typephi
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   1.1 GB: 3-of-3
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.38.0.dev0
Tokenizer ClassCodeGenTokenizer
Padding Token<|im_end|>
Vocabulary Size50297
Torch Data Typefloat32

Best Alternatives to Damysus 2.7B Chat

Best Alternatives
Context / RAM
Downloads
Likes
PhigRange DPO2K / 5.6 GB141
PhigRange 2.7B Slerp2K / 5.6 GB60
JSL MedPhi2 2.7B2K / 5.6 GB28203
Speculor 2.7B2K / 5.6 GB1862
...atural Language To Cypher 2.7B2K / 5.6 GB450
Codephi 2.7B2K / 5.6 GB60
Phi 2.7B MERGED0K / 5.6 GB1290
Samanthav2 2.7B0K / 5.6 GB441
Barcenas 2.7B0K / 5.6 GB141
Damysus 2.7B Chat GGUF2K / 1.7 GB690
Note: green Score (e.g. "73.2") means that the model is better than prince-canuma/Damysus-2.7B-Chat.

Rank the Damysus 2.7B Chat 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? 43470 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