What are the hardware requirements for Lilac Sft?

Lilac Sft requires approximately 2.8 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Lilac Sft and how large is it?

Lilac Sft is developed by semran1, a model with 1.4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Lilac Sft?

Lilac Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Lilac Sft by semran1 — VRAM 2.8GB, 2K context

Name: Lilac Sft
Author: semran1

Lilac Sft is an open-source language model by semran1. Features: 1.4b LLM, VRAM: 2.8GB, Context: 2K, LLM Explorer Score: 0.17.

Autotrain compatible Base model:finetune:semran1/te... Base model:semran1/test-57 8 a... Conversational Endpoints compatible Generated from trainer Phi Region:us Safetensors Sft Tensorboard Trl

Model Card on HF 🤗: https://huggingface.co/semran1/lilac-sft

Lilac Sft Parameters and Internals

LLM Name	Lilac Sft
Repository 🤗	https://huggingface.co/semran1/lilac-sft
Model Name	lilac-sft
Base Model(s)	Test 57 8 Avg semran1/test-57_8_avg
Model Size	1.4b
Required VRAM	2.8 GB
Updated	2025-03-02
Maintainer	semran1
Model Type	phi
Model Files	2.8 GB 0.0 GB
Model Architecture	QPhiForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.48.3
Tokenizer Class	CodeGenTokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	50297
Torch Data Type	bfloat16

Rank the Lilac Sft capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Lilac Sft

Best Alternatives	Context / RAM	Downloads
Test 578	2K / 2.8 GB	384
Test 57 8 Avg	2K / 2.8 GB	289
Lilac Sft Hermes	2K / 2.8 GB	38
Lilac Sft Inf	2K / 2.8 GB	23

Note: green Score (e.g. "73.2") means that the model is better than semran1/lilac-sft.