Phi 3 Mini 4K Instruct by unsloth

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

  Autotrain compatible   Conversational   En   Endpoints compatible   Instruct   Mistral   Phi   Phi3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Phi 3 Mini 4K Instruct Benchmarks

Phi 3 Mini 4K Instruct (unsloth/Phi-3-mini-4k-instruct)

Phi 3 Mini 4K Instruct Parameters and Internals

Model Type 
text generation, transformers
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
text generation, model finetuning
Additional Notes 
The model can be directly quantized to 4bit using 'bitsandbytes'.
LLM NamePhi 3 Mini 4K Instruct
Repository ๐Ÿค—https://huggingface.co/unsloth/Phi-3-mini-4k-instruct 
Model Size3.8b
Required VRAM7.6 GB
Updated2025-02-22
Maintainerunsloth
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Quantized Models of the Phi 3 Mini 4K Instruct

Model
Likes
Downloads
VRAM
Scm Phi3 Q4 K M V30192 GB
...in 2.9.1 Phi 3 Kensho 4.5B AWQ0843 GB
Scm Phi3 Q80104 GB
Scm Phi3 Q5 K M V30102 GB
Scm Phi3 16 V30107 GB
Scm Phi3 Q8 V3124 GB
Scm Phi3 Q4 K M052 GB
...Sentiment May 24 2024 2epoches0747 GB
Dj Phi 3 F16 GGUF0407 GB
Dj Phi 3 3.8B 16bit0147 GB

Best Alternatives to Phi 3 Mini 4K Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Llama Phi 3 DoRA4K / 7.6 GB1166
Empty Phi 3 Mini4K / 7.6 GB760
...ling Assistant Spanish Pofi V24K / 7.7 GB330
...i3 Short Story Merged Bfloat164K / 7.6 GB291
Phi 3 Mini 4K Instruct Orpo V24K / 14.9 GB91
... Instruct Unsloth Merged 16bit4K / 7.6 GB271
...Word Problems 200K Model 16bit4K / 7.6 GB38790
Porpoise14K / 7.6 GB4270
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB760
...100 Percent Low Med Perplexity4K / 7.6 GB800

Rank the Phi 3 Mini 4K Instruct 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227