What are the hardware requirements for Excalibur 7B DPO?

Excalibur 7B DPO requires approximately 14.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Excalibur 7B DPO and how large is it?

Excalibur 7B DPO is developed by InferenceIllusionist, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Excalibur 7B DPO perform on standard benchmarks?

Excalibur 7B DPO has the following published scores: MMLU 65.46. Compare against reference models on this page or on the LLM Explorer leaderboards.

Excalibur 7B DPO by InferenceIllusionist — VRAM 14.4GB, 32K context

Name: Excalibur 7B DPO
Author: InferenceIllusionist

Excalibur 7B DPO is an open-source language model by InferenceIllusionist. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 70.9, HellaSwag: 87.9, MMLU: 65.5, GSM8K: 65.4.

Base model:finetune:inferencei... Base model:inferenceillusionis... Chatml Dataset:intel/orca dpo pairs Dpo Endpoints compatible Finetuned Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO

Excalibur 7B DPO Parameters and Internals

Model Type

text-generation

Additional Notes

An initial foray into the world of fine-tuning aiming to amplify model's response quality for vision use cases.

Training Details

Data Sources:

Intel/orca_dpo_pairs

Methodology:

Direct Preference Optimization (DPO)

Training Time:

a little over an hour

Hardware Used:

single A100 GPU

Input Output

Input Format:

ChatML for best results, Alpaca may also work

LLM Name	Excalibur 7B DPO
Repository 🤗	https://huggingface.co/InferenceIllusionist/Excalibur-7b-DPO
Base Model(s)	Excalibur 7B InferenceIllusionist/Excalibur-7b
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-07-09
Maintainer	InferenceIllusionist
Model Type	mistral
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	float16

Rank the Excalibur 7B DPO 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 Excalibur 7B DPO

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than InferenceIllusionist/Excalibur-7b-DPO.