Phi 3 Mini 4K Instruct V0 Bnb 4bit by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Phi 3 Mini 4K Instruct V0 Bnb 4bit   URL Share it on

  4-bit   4bit   Autotrain compatible   Bitsandbytes   Conversational   En   Endpoints compatible   Instruct   Mistral   Phi   Phi3   Quantized   Region:us   Safetensors   Unsloth

Phi 3 Mini 4K Instruct V0 Bnb 4bit 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 Mini 4K Instruct V0 Bnb 4bit (unsloth/Phi-3-mini-4k-instruct-v0-bnb-4bit)

Phi 3 Mini 4K Instruct V0 Bnb 4bit Parameters and Internals

Model Type 
text generation
Release Notes 
Notes:
Unsloth provides beginner-friendly notebooks for finetuning models using less memory.
LLM NamePhi 3 Mini 4K Instruct V0 Bnb 4bit
Repository ๐Ÿค—https://huggingface.co/unsloth/Phi-3-mini-4k-instruct-v0-bnb-4bit 
Model Size2.1b
Required VRAM2.3 GB
Updated2024-12-22
Maintainerunsloth
Model Typemistral
Instruction-BasedYes
Model Files  2.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.43.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Mini 4K Instruct V0 Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...hi 3 Mini 4K Instruct Bnb 4bit4K / 2.3 GB1272627
Phi 4K Gsm8k4K / 2.3 GB190
Phi 3 Autocomplete Search4K / 2.3 GB110
Small Mistral 14K / 2.3 GB120
Phi3 Mini New Model Demo24K / 2.3 GB170
MediChat Medium4K / 2.3 GB101
Hf4K / 2.3 GB90
Recophi3 4bit4K / 2.3 GB170
Phi3 MeetingQA 4bit4K / 2.3 GB200
...3 Mini 4K Instruct Ita Orpo V24K / 2.3 GB160
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Phi-3-mini-4k-instruct-v0-bnb-4bit.

Rank the Phi 3 Mini 4K Instruct V0 Bnb 4bit 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217