LLM EXPLORER 62,857 MODELS INDEXED

FaithEyes 8B SFT by Jackwang111

By Jackwang111 · 23 downloads
HF Repo ↗ Copy URL

FaithEyes 8B SFT is an open-source language model by Jackwang111. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

  Arxiv:2607.28225   Agentic-vlm Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-in...   Code-generation   Conversational   En   Faithfulness   Image-text-to-text   Instruct   Qwen3 vl   Region:us   Safetensors   Tool-use   Vision   Vision-language-model
Model Card on HF 🤗: https://huggingface.co/Jackwang111/FaithEyes-8B-SFT 

FaithEyes 8B SFT Parameters and Internals

LLM NameFaithEyes 8B SFT
Repository 🤗https://huggingface.co/Jackwang111/FaithEyes-8B-SFT 
Base Model(s)  Qwen3 VL 8B Instruct   Qwen/Qwen3-VL-8B-Instruct
Model Size8b
Required VRAM17.5 GB
Updated2026-10-03
MaintainerJackwang111
Model Typeqwen3_vl
Instruction-BasedYes
Model Files  17.5 GB
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.16.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to FaithEyes 8B SFT

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
PhysBrain1.5 8B0K / 17.8 GB63827
Qwen3vl Resume Parser0K / 17.5 GB2574553
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
ArmorOCR0K / 17.5 GB1959
FaithEyes 8B RL0K / 17.5 GB250
Qwen3 VL 8B VQA SFT0K / 17.5 GB1990
Invoice Split 20220K / 17.5 GB180
GUI Owl 1.5 8B Instruct0K / 17.5 GB488213
Note: green Score (e.g. "73.2") means that the model is better than Jackwang111/FaithEyes-8B-SFT.