Phi 3.5 Mini ChatML by bunnycore

 ยป  All LLMs  ยป  bunnycore  ยป  Phi 3.5 Mini ChatML   URL Share it on

  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:bunnycore/phi-3.1-e... Base model:bunnycore/phi-3.5-m... Base model:bunnycore/phi-3.5-m... Base model:bunnycore/phi-3.5-m... Base model:bunnycore/phi-3.5-s... Base model:sicariussicariistuf...   Conversational   Custom code   Endpoints compatible   Instruct   Lora   Phi3   Region:us   Safetensors   Sharded   Tensorflow

Phi 3.5 Mini ChatML Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Phi 3.5 Mini ChatML Parameters and Internals

LLM NamePhi 3.5 Mini ChatML
Repository ๐Ÿค—https://huggingface.co/bunnycore/Phi-3.5-Mini-ChatML 
Base Model(s)  bunnycore/Phi-3.5-Mini-Sonet-RP-V2   bunnycore/Phi-3.1-EvolKit-lora   bunnycore/Phi-3.5-Mini-Sonet-RP-V2   bunnycore/Phi-3.5-Sonet-RP-ChatML   SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored   bunnycore/Phi-3.5-Sonet-RP-ChatML   bunnycore/Phi-3.5-Mini-Sonet-RP   bunnycore/Phi-3.5-mini-System-lora   bunnycore/Phi-3.5-Mini-Sonet-RP-V2   bunnycore/Phi-3.1-EvolKit-lora   bunnycore/Phi-3.5-Mini-Sonet-RP-V2   bunnycore/Phi-3.5-Sonet-RP-ChatML   SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored   bunnycore/Phi-3.5-Sonet-RP-ChatML   bunnycore/Phi-3.5-Mini-Sonet-RP   bunnycore/Phi-3.5-mini-System-lora
Merged ModelYes
Model Size3.8b
Required VRAM7.7 GB
Updated2024-09-18
Maintainerbunnycore
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
LoRA ModelYes
Torch Data Typebfloat16
Phi 3.5 Mini ChatML (bunnycore/Phi-3.5-Mini-ChatML)

Best Alternatives to Phi 3.5 Mini ChatML

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB365313466
Phi 3 Mini 128K Instruct128K / 7.7 GB1930021568
Flow Judge V0.1128K / 7.7 GB8018
Phi 3.5 Mini ITA128K / 7.7 GB52639
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB5958
....5 Mini 3.8B ArliAI RPMax V1.1128K / 7.7 GB655
Borea Phi 3.5 Mini Instruct Jp128K / 7.7 GB2025
SeaPhi3 Mini128K / 7.7 GB39414
Phi 3 Mini 128K Instruct FP8128K / 4 GB3230
...i 128K Instruct Abliterated V3128K / 7.7 GB49312
Note: green Score (e.g. "73.2") means that the model is better than bunnycore/Phi-3.5-Mini-ChatML.

Rank the Phi 3.5 Mini ChatML Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 36026 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803