Modelpublic

reallexi/lexi-coder-v4.1

sourceHugging Faceotherupdated 2mo agoView on Hugging Face

4likes307downloads

Model Card

reallexi/lexi-coder-v4.1

A GGUF build of 3.85B parameters, derived from `microsoft/Phi-4-mini-instruct`.

Size and requirements


Parameters	3,847,556,096 (3.85B)
Weights on disk	9.48 GB
Quantization	Q4KM
Trained context length	1,024 tokens
Base model	`microsoft/Phi-4-mini-instruct`

Approximate memory to hold the weights. Add context and runtime overhead on top.

Precision	Weights
FP16 / BF16	7.17 GB
8-bit (Q8_0)	3.58 GB
4-bit (Q4KM)	1.97 GB

Training


Strategy	lora
Adapter	Auto LoRA
LoRA rank / alpha	8 / 16
Dataset	`ianncity/GLM-5.2-Conversation`
Samples learned	50,296 (through phase 11 of 20)
Training steps	370
Epochs	5

Usage

bash

llama-cli -m reallexi/lexi-coder-v4.1.gguf -p "Your prompt here"

License and attribution

The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.

—Base model: `microsoft/Phi-4-mini-instruct`

—Training data: ianncity/GLM-5.2-Conversation

Produced by Reallexi LLC AI Model Builder from training job #1472. Core: https://llm.reallexi.io