LLM EXPLORER 58,133 MODELS INDEXED

Coder Phi 3 Mini 4K Instruct by candenizkocak

By candenizkocak · 13 downloads
HF Repo ↗ Copy URL

Coder Phi 3 Mini 4K Instruct is an open-source language model by candenizkocak. Features: 3.8b LLM, VRAM: 7.7GB, Context: 4K, Instruction-Based, Code Generating, LLM Explorer Score: 0.12.

  Autotrain compatible   Codegen   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/candenizkocak/coder-Phi-3-mini-4k-instruct 

Coder Phi 3 Mini 4K Instruct Parameters and Internals

Additional Notes 
This model is fine-tuned to better answer questions related to programming.
Training Details 
Data Sources:
m-a-p/Code-Feedback
Methodology:
Fine-tuning by making small modifications on sample_finetune.py
Hardware Used:
A100 on Google Colab
LLM NameCoder Phi 3 Mini 4K Instruct
Repository 🤗https://huggingface.co/candenizkocak/coder-Phi-3-mini-4k-instruct 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-05-17
Maintainercandenizkocak
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Generates CodeYes
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Coder Phi 3 Mini 4K Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Omega Coder Phi 3 Mini 1K4K / 15.4 GB50
Lexi Coder V4.3128K / 7.7 GB3091
Note: green Score (e.g. "73.2") means that the model is better than candenizkocak/coder-Phi-3-mini-4k-instruct.