What are the hardware requirements for Llama2 CodeGen PEFT QLoRA?

Llama2 CodeGen PEFT QLoRA requires approximately 13.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llama2 CodeGen PEFT QLoRA and how large is it?

Llama2 CodeGen PEFT QLoRA is developed by AhmedSSoliman. 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 Llama2 CodeGen PEFT QLoRA?

Llama2 CodeGen PEFT QLoRA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llama2 CodeGen PEFT QLoRA by AhmedSSoliman — VRAM 13.5GB

Name: Llama2 CodeGen PEFT QLoRA
Author: AhmedSSoliman

Llama2 CodeGen PEFT QLoRA is an open-source language model by AhmedSSoliman. Features: LLM, VRAM: 13.5GB, Code Generating, LLM Explorer Score: 0.08.

Autotrain Code Code-generation Codegen Coding Dataset:ahmedssoliman/codesear... Dataset:ahmedssoliman/codesear... Endpoints compatible Llama Llama2 Lora Peft Pytorch Qlora Region:us Sharded Tensorboard

Model Card on HF 🤗: https://huggingface.co/AhmedSSoliman/Llama2-CodeGen-PEFT-QLoRA

Llama2 CodeGen PEFT QLoRA Parameters and Internals

Model Type

code-generation

Training Details

Data Sources:

CodeSearchNet dataset

Methodology:

fine-tuning

LLM Name	Llama2 CodeGen PEFT QLoRA
Repository 🤗	https://huggingface.co/AhmedSSoliman/Llama2-CodeGen-PEFT-QLoRA
Required VRAM	13.5 GB
Updated	2026-10-21
Maintainer	AhmedSSoliman
Model Files	0.1 GB 10.0 GB: 1-of-2 3.5 GB: 2-of-2 0.0 GB
Generates Code	Yes
Model Architecture	AutoModelForCausalLM
Is Biased	none
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj
LoRA Alpha	64
LoRA Dropout	0.1
R Param	32

Rank the Llama2 CodeGen PEFT QLoRA 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 Llama2 CodeGen PEFT QLoRA

Best Alternatives	Context / RAM	Downloads	Likes
...llama PY CODER 4bit Lora 4k V9	0K / 0.4 GB	18	0
...llama PY CODER 4bit Lora 4k V8	0K / 0.4 GB	21	0

Note: green Score (e.g. "73.2") means that the model is better than AhmedSSoliman/Llama2-CodeGen-PEFT-QLoRA.