What are the hardware requirements for Codelica?

Codelica requires approximately 16.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codelica and how large is it?

Codelica is developed by neighborwang, a model with 8b 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 Codelica?

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

Codelica by neighborwang — VRAM 16.1GB

Name: Codelica
Author: neighborwang

Codelica is an open-source language model by neighborwang. Features: 8b LLM, VRAM: 16.1GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14.

Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Dataset:neighborwang/modelica ... En Endpoints compatible Instruct Llama Lora Peft Region:us Safetensors Sharded Tensorboard Tensorflow

Model Card on HF 🤗: https://huggingface.co/neighborwang/Codelica

Codelica Parameters and Internals

Model Type

text2text-generation

Additional Notes

A cutting-edge LLM designed to empower users of all skill levels to effortlessly model complex systems and unlock the full potential of Modelica.

Supported Languages

en (high)

LLM Name	Codelica
Repository 🤗	https://huggingface.co/neighborwang/Codelica
Base Model(s)	meta-llama/Llama-3.1-8B-Instruct meta-llama/Llama-3.1-8B-Instruct
Model Size	8b
Required VRAM	16.1 GB
Updated	2024-10-07
Maintainer	neighborwang
Instruction-Based	Yes
Model Files	0.2 GB 5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4 0.0 GB
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	o_proj\|down_proj\|v_proj\|q_proj\|k_proj\|gate_proj\|up_proj
LoRA Alpha	32
LoRA Dropout	0.05
R Param	16

Rank the Codelica 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 Codelica

Best Alternatives	Context / RAM	Downloads	Likes
Llama 3.1 8B Instuct Uz	128K / 16.1 GB	1000	15
...ertus 8B Financial Reasoner V2	0K / 0.2 GB	23	2
Cve Model	0K / 0.3 GB	16	0
Shaista Pro	0K / 0 GB	10	0
ConfTuner Ministral	0K / 16.1 GB	13	4
Autotrain Pvqlj Odah2	0K / 0.2 GB	18	0
500tiao 100lun	0K / 0.2 GB	7	0
...8B Instruct Shimshimi 500 Ver2	0K / 16.1 GB	9	0
ModeliCo 8B	0K / 16.1 GB	4	2
Llama31 Eros	0K / 16.1 GB	21	1

Note: green Score (e.g. "73.2") means that the model is better than neighborwang/Codelica.