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 GPTQ by 4bit

 »  All LLMs  »  4bit  »  Redmond Puffin 13B GPTQ   URL Share it on

  5   
  4bit   Autotrain compatible   Eng   Gptq   Llama   Llama2   Quantized   Region:us   Sft
Model Card on HF 🤗: https://huggingface.co/4bit/Redmond-Puffin-13B-GPTQ 

Redmond Puffin 13B GPTQ 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: 0.12185
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 GPTQ (4bit/Redmond-Puffin-13B-GPTQ)
🌟 Advertise your project 🚀

Redmond Puffin 13B GPTQ Parameters and Internals

Model Type 
text generation
Additional Notes 
Some token mismatch problems and formatting issues identified.
Training Details 
Data Sources:
3,000 carefully curated GPT-4 examples, CamelAI's Physics, Chemistry, Biology and Math
Data Volume:
2 trillion tokens
Methodology:
Pretrained with a context length of 4096 tokens, fine-tuned on multi-turn conversations
Context Length:
4096
Model Architecture:
GPTQ, fine-tuned llama-2-based
Input Output 
Input Format:
### human:
Accepted Modalities:
text
Output Format:
### gpt:
LLM NameRedmond Puffin 13B GPTQ
Repository 🤗https://huggingface.co/4bit/Redmond-Puffin-13B-GPTQ 
Base Model(s)  Redmond Puffin 13B   4bit/Redmond-Puffin-13B
Model Size13b
Required VRAM7.3 GB
Updated2025-09-23
Maintainer4bit
Model Typellama
Model Files  7.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licenseother
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

Best Alternatives to Redmond Puffin 13B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB1016
LongAlign 13B 64K GPTQ64K / 7.3 GB61
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB73
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB121
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB63
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB64
EverythingLM 13B 16K GPTQ16K / 7.3 GB1414
LlongOrca 13B 16K GPT16K / 7.3 GB70
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB61
Tinybra 13B GPTQ 4BIT16K / 7 GB60
Note: green Score (e.g. "73.2") means that the model is better than 4bit/Redmond-Puffin-13B-GPTQ.

Rank the Redmond Puffin 13B GPTQ 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? 51534 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