Phi 2 Instruct V1 by timothyckl

 ยป  All LLMs  ยป  timothyckl  ยป  Phi 2 Instruct V1   URL Share it on

  Autotrain compatible   Custom code   Endpoints compatible   Ggml   Gguf   Instruct   Phi   Quantized   Region:us   Safetensors   Sharded   Tensorboard   Tensorflow

Phi 2 Instruct V1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 Instruct V1 (timothyckl/phi-2-instruct-v1)

Phi 2 Instruct V1 Parameters and Internals

Model Type 
fine-tuned model
Training Details 
Data Sources:
c-s-ale/alpaca-gpt4-data dataset
Data Volume:
9k samples
Training Time:
1 epoch
Input Output 
Input Format:
### INSTRUCTION: {instruction} ### INPUT: {input} ### RESPONSE: {output}
LLM NamePhi 2 Instruct V1
Repository ๐Ÿค—https://huggingface.co/timothyckl/phi-2-instruct-v1 
Model Size2.8b
Required VRAM11.1 GB
Updated2025-02-22
Maintainertimothyckl
Model Typephi
Instruction-BasedYes
Model Files  1.7 GB   2.0 GB   5.0 GB: 1-of-3   5.0 GB: 2-of-3   1.1 GB: 3-of-3
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitecturePhiForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.39.3
Tokenizer ClassCodeGenTokenizer
Vocabulary Size51200
Torch Data Typefloat32

Best Alternatives to Phi 2 Instruct V1

Best Alternatives
Context / RAM
Downloads
Likes
Phi 2 Instruct V0.12K / 5.6 GB1062
Phi 2 Instruct Apo2K / 5.6 GB150
EEVE Korean Instruct 2.8B V1.02K / 5.7 GB275222
Att Model2K / 5.7 GB500
Eeve2.8 Base2K / 5.7 GB60
Eeve2.8 Ko2K / 5.7 GB100
... Instruct 2.8B V1.0 20240430 22K / 2.9 GB590
Phi 2 Code Instruct2K / 5.6 GB444
Dolphin 2 6 Phi 20K / 5.6 GB338192
Phi 2 Evol Instruct Chinese0K / 5.6 GB04
Note: green Score (e.g. "73.2") means that the model is better than timothyckl/phi-2-instruct-v1.

Rank the Phi 2 Instruct V1 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