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

Phasmid 1 5 V0.5 by SE6446

 »  All LLMs  »  SE6446  »  Phasmid 1 5 V0.5   URL Share it on

  19   

Phasmid 1 5 V0.5 is an open-source language model by SE6446. Features: LLM, VRAM: 2.8GB, License: mit, LLM Explorer Score: 0.1.

  Conversational   Custom code   Dataset:pygmalionai/pippa Dataset:se6446/pippa alpaca co...   Mixformer-sequential   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/SE6446/Phasmid-1_5-V0_5 

Phasmid 1 5 V0.5 Benchmarks

LLME Score: 0.10175
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phasmid 1 5 V0.5 (SE6446/Phasmid-1_5-V0_5)
🌟 Advertise your project 🚀

Phasmid 1 5 V0.5 Parameters and Internals

Model Type 
conversational
Use Cases 
Areas:
Research
Limitations:
Due to the nature of the dataset, the model can produce NSFW response in certain scenarios.
Considerations:
Consider applying a filter for SFW.
Additional Notes 
This model is a fine-tuned version of microsoft/phi-1_5 on the PIPPA dataset. The model suffers from problematic hallucinations and may produce erratic outputs.
Training Details 
Data Sources:
SE6446/Pippa_alpaca_completion, PygmalionAI/PIPPA
Input Output 
Input Format:
### Instruction: {Character card infomation} ### Input: {{user}}: {{prompt}}
Output Format:
{{char}}:
LLM NamePhasmid 1 5 V0.5
Repository 🤗https://huggingface.co/SE6446/Phasmid-1_5-V0_5 
Required VRAM2.8 GB
Updated2025-12-24
MaintainerSE6446
Model Typemixformer-sequential
Model Files  2.8 GB   0.0 GB
Model ArchitectureMixFormerSequentialForCausalLM
Licensemit
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typebfloat16
Activation Functiongelu_new

Best Alternatives to Phasmid 1 5 V0.5

Best Alternatives
Context / RAM
Downloads
Likes
Phi 20K / 11.1 GB1622
The OverThinker Phi 1 50K / 2.8 GB77
Phi Ko1ep0K / 2.8 GB50
Scarlett Phi0K / 2.8 GB68
IF PromptMKR Phi0K / 2.8 GB32
Oo Phi 1 50K / 2.8 GB4132
Puffin Phi V20K / 2.8 GB1439
Samantha Phi0K / 2.8 GB1127
Samantha Phi0K / 2.8 GB827
Phi Gath0K / 2.8 GB60
Note: green Score (e.g. "73.2") means that the model is better than SE6446/Phasmid-1_5-V0_5.

Rank the Phasmid 1 5 V0.5 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer