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

Pipi by huggingfacepremium

 »  All LLMs  »  huggingfacepremium  »  Pipi   URL Share it on

  13   
  Autotrain compatible   Code   Conversational   En   Endpoints compatible   Gguf   Instruct   Lora   Mistral   Quantized   Region:us   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/huggingfacepremium/pipi 

Pipi Benchmarks

LLME Score: 0.16277
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pipi (huggingfacepremium/pipi)
🌟 Advertise your project 🚀

Pipi Parameters and Internals

Model Type 
text generation, chat format
Use Cases 
Areas:
commercial, research
Applications:
memory/compute constrained environments, latency bound scenarios, strong reasoning, long context
Primary Use Cases:
acceleration of research on language and multimodal models, building generative AI features
Limitations:
Not specifically designed or evaluated for all downstream purposes.
Considerations:
Developers should adhere to laws, mitigate against bias and inaccuracies.
Additional Notes 
Model is well-suited for research and generative AI applications with focus on strong reasoning capabilities and long context.
Supported Languages 
en (primary)
Training Details 
Data Sources:
Phi-3 datasets, synthetic data, filtered publicly available websites
Data Volume:
3.3T tokens
Methodology:
Supervised fine-tuning and Direct Preference Optimization
Context Length:
128000
Training Time:
7 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer
Safety Evaluation 
Methodologies:
Post-training supervised fine-tuning and direct preference optimization for safety.
Findings:
Unfairness, unreliability, or offensive content may still be present despite safety post-training.
Risk Categories:
Quality of Service, Representation of Harms & Stereotypes, Inappropriate/Offensive Content, Information Reliability, Limited Scope for Code
Ethical Considerations:
Developers should evaluate safety and fairness before using in high risk scenarios.
Responsible Ai Considerations 
Fairness:
Model may over- or under-represent groups or reinforce stereotypes.
Transparency:
Developers should inform end-users that they are interacting with an AI system.
Accountability:
Developers are responsible for ensuring compliant use in specific scenarios.
Mitigation Strategies:
Consider transparency and mitigate risks in high-risk scenarios.
Input Output 
Input Format:
Chat format (e.g., <|user|> prompt format).
Accepted Modalities:
text
Output Format:
Generated text in response to input.
Performance Tips:
Provide inputs in chat format for best results.
Release Notes 
Version:
4K
Date:
February to April 2024
Notes:
Trained between February and April 2024, on 3.3T tokens.
LLM NamePipi
Repository 🤗https://huggingface.co/huggingfacepremium/pipi 
Required VRAM2.4 GB
Updated2024-12-10
Maintainerhuggingfacepremium
Instruction-BasedYes
Model Files  2.4 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModelForCausalLM
Licensemit
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|down_proj|v_proj|o_proj|q_proj|up_proj|k_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Pipi

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Python0K / 7.6 GB1381
...emo Instruct 2407 EXL2 8bpw H80K / 12.6 GB137
Dre Phi0K / 7.6 GB50
Phi 3 Mini 4K CodeInstruct0K / 7.6 GB50
...3 Mini 4K Instruct Text To Sql0K / 7.6 GB160
VLM2Vec LoRA0K / 0 GB3111
... Mini 4K Instruct Chinese Lora0K / 0 GB76
Falcon Camel Math Instruct0K / 0 GB51
Instruct Igel 0010K / 12.9 GB1147
Note: green Score (e.g. "73.2") means that the model is better than huggingfacepremium/pipi.

Rank the Pipi 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