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

Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2 by Zoyd

 »  All LLMs  »  Zoyd  »  Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2   URL Share it on

  9   
  3-bit   Autotrain compatible   Code   Conversational   Custom code   Endpoints compatible   Exl2   Instruct   Multilingual   Phi3   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Zoyd/failspy_Phi-3-mini-4k-geminified-3_0bpw_exl2 

Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2 Benchmarks

LLME Score: 0.18709
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2 (Zoyd/failspy_Phi-3-mini-4k-geminified-3_0bpw_exl2)

Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model uses orthogonalized bfloat16 safetensor weights, with a methodology described in the paper/blog post 'Refusal in LLMs is mediated by a single direction'.
Supported Languages 
multilingual (Yes)
LLM NameFailspy Phi 3 Mini 4K Geminified 3 0bpw EXL2
Repository 🤗https://huggingface.co/Zoyd/failspy_Phi-3-mini-4k-geminified-3_0bpw_exl2 
Required VRAM1.6 GB
Updated2025-03-12
MaintainerZoyd
Model Typephi3
Instruction-BasedYes
Model Files  1.6 GB
Quantization Typeexl2
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...m 128K Instruct 8.0bpw H8 EXL2128K / 13.4 GB194
...m 128K Instruct 6.0bpw H6 EXL2128K / 10.7 GB163
...dium 128K Instruct 8 0bpw EXL2128K / 13.4 GB111
...m 128K Instruct 3.0bpw H6 EXL2128K / 5.6 GB80
...m 128K Instruct 5.0bpw H6 EXL2128K / 8.9 GB80
...128K Instruct HQQ 4bit Smashed128K / 2.3 GB520
...128K Instruct HQQ 2bit Smashed128K / 1.4 GB400
...28K Instruct Ov Fp16 Int4 Asym128K / 2.5 GB200
Phi 3 Mini 4K Instruct Fp164K /  GB5284
NuExtract Bpw6 EXL24K / 3 GB121
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/failspy_Phi-3-mini-4k-geminified-3_0bpw_exl2.

Rank the Failspy Phi 3 Mini 4K Geminified 3 0bpw EXL2 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? 44902 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