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

Redmond Puffin 13B by NousResearch

 »  All LLMs  »  NousResearch  »  Redmond Puffin 13B   URL Share it on

  1858   
  Autotrain compatible   Dataset:ldjnr/puffin   Endpoints compatible   Eng   Llama   Llama2   Pytorch   Region:us   Sft   Sharded
Model Card on HF 🤗: https://huggingface.co/NousResearch/Redmond-Puffin-13B 

Redmond Puffin 13B Benchmarks

ARC: 60.49 vs 96.7 (so35)-37.4%
HellaSwag: 83.21 vs 95.3 (gpt4)-12.7%
MMLU: 54.95 vs 88.3 (so35)-37.8%
TruthfulQA: 42.08 vs 59 (gpt4)-28.7%
WinoGrande: 76.48 vs 87.5 (gpt4)-12.6%
GSM8K: 11.22 vs 96.4 (so35)-88.4%
LLME Score: 0.1454
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Redmond Puffin 13B (NousResearch/Redmond-Puffin-13B)
🌟 Advertise your project 🚀

Redmond Puffin 13B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Primary Use Cases:
Multi-turn conversations, Long context communication
Additional Notes 
The first commercially available model by Nous Research. Currently facing token mismatch problems, expected to be addressed in future updates.
Training Details 
Data Sources:
GPT-4 conversations, CamelAI's Physics dataset, CamelAI's Chemistry dataset, CamelAI's Biology dataset, CamelAI's Math dataset
Data Volume:
3,000 curated examples
Methodology:
Fine-tuning
Context Length:
4096
Hardware Used:
Sponsored by Redmond AI
Input Output 
Input Format:
USER: ASSISTANT:
Performance Tips:
Avoid using previous incorrect prefixes, now corrected to USER: ASSISTANT:
LLM NameRedmond Puffin 13B
Repository 🤗https://huggingface.co/NousResearch/Redmond-Puffin-13B 
Model Size13b
Required VRAM26 GB
Updated2025-09-23
MaintainerNousResearch
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32032
Torch Data Typebfloat16

Quantized Models of the Redmond Puffin 13B

Model
Likes
Downloads
VRAM
Redmond Puffin 13B GGUF23265 GB
Redmond Puffin 13B AWQ187 GB
Redmond Puffin 13B GPTQ26147 GB
Redmond Puffin 13B GGML2385 GB

Best Alternatives to Redmond Puffin 13B

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB60
Yarn Llama 2 13B 128K128K / 26 GB34112
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB50
LongAlign 13B 64K64K / 26 GB11513
LongAlign 13B 64K Base64K / 26 GB923
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB64
Openbuddy Llama2 13b64k V1564K / 26.1 GB52
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Redmond-Puffin-13B.

Rank the Redmond Puffin 13B 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? 51536 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