Phi 3.5 Mini Instruct by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Phi 3.5 Mini Instruct   URL Share it on

  Arxiv:2404.14219   Arxiv:2407.13833   Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-m...   Conversational   Endpoints compatible   Instruct   Llama   Microsoft   Multilingual   Phi   Phi3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth

Phi 3.5 Mini Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Phi 3.5 Mini Instruct Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
commercial, research
Applications:
general purpose AI systems, memory/compute constrained environments, latency bound scenarios, strong reasoning scenarios
Primary Use Cases:
language modeling, multilingual tasks, reasoning tasks
Limitations:
limited factual knowledge storage, susceptible to generating repetitive or inconsistent responses in long sessions
Considerations:
Developers are advised to evaluate and mitigate for accuracy, safety, and fairness before deploying.
Additional Notes 
Phi-3.5-mini can be used with or without flash attention implementation depending on GPU capabilities.
Supported Languages 
Arabic (supported), Chinese (supported), Czech (supported), Danish (supported), Dutch (supported), English (supported), Finnish (supported), French (supported), German (supported), Hebrew (supported), Hungarian (supported), Italian (supported), Japanese (supported), Korean (supported), Norwegian (supported), Polish (supported), Portuguese (supported), Russian (supported), Spanish (supported), Swedish (supported), Thai (supported), Turkish (supported), Ukrainian (supported)
Training Details 
Data Sources:
publicly available documents, synthetic data, high-quality educational data, code
Data Volume:
3.4 trillion tokens
Methodology:
supervised fine-tuning, proximal policy optimization, direct preference optimization
Context Length:
128000
Training Time:
10 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
dense decoder-only Transformer
Safety Evaluation 
Methodologies:
red teaming, adversarial conversation simulations, multilingual safety evaluation benchmark datasets
Findings:
The model may refuse to generate undesirable outputs in English even when requested in another language., More susceptible to longer multi-turn jailbreak techniques across languages.
Risk Categories:
misinformation, offensive content, perpetuation of stereotypes
Ethical Considerations:
It highlights the need for industry-wide investment in high-quality safety evaluation datasets across multiple languages and risk areas.
Responsible Ai Considerations 
Fairness:
Models may reflect real-world patterns and societal biases.
Transparency:
Models provide simple AI-driven outputs without additional operational transparency measures.
Accountability:
Users are encouraged to pair the model with larger AI systems for better contextual and application-specific outcomes.
Mitigation Strategies:
Fine-tuning with additional safety datasets and building application-level safeguards are recommended.
Input Output 
Input Format:
chat format
Accepted Modalities:
text
Output Format:
generated text in response to the input
Performance Tips:
To use flash attention, ensure using suitable GPU hardware.
Release Notes 
Version:
Phi-3.5-mini
Date:
August 2024
Notes:
Updated with post-training data for gains in multilingual and reasoning capability.
LLM NamePhi 3.5 Mini Instruct
Repository ๐Ÿค—https://huggingface.co/unsloth/Phi-3.5-mini-instruct 
Base Model(s)  microsoft/Phi-3.5-mini-instruct   microsoft/Phi-3.5-mini-instruct
Model Size3.8b
Required VRAM7.6 GB
Updated2024-12-04
Maintainerunsloth
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.44.1
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16
Phi 3.5 Mini Instruct (unsloth/Phi-3.5-mini-instruct)

Best Alternatives to Phi 3.5 Mini Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 5 Mini Kp 12k Cfr Sft128K / 7.6 GB4850
Phi 3 5 Mini Tictactoe1200128K / 7.6 GB830
...3 Mini 128K Instruct LLaMAfied128K / 7.6 GB413
Llamaphi 3 128K Instruct128K / 7.6 GB81
...i 3 Mini 4K Instruct LLaMAfied4K / 7.6 GB54511
Phillama 3.8B V0.14K / 7.6 GB1010
Phillama 3.8B V14K / 7.6 GB105
Phi 3 5 Mini 3k Each128K / 7.6 GB350
...nder Llamafied With 16bit GGUF4K / 7.6 GB460

Rank the Phi 3.5 Mini 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? 38813 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124