LLM EXPLORER 62,857 MODELS INDEXED

FaithEyes 7B SFT by Jackwang111

By Jackwang111 · 19 downloads
HF Repo ↗ Copy URL

FaithEyes 7B SFT is an open-source language model by Jackwang111. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

  Arxiv:2607.28225   Agentic-vlm Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-...   Code-generation   Conversational   En   Faithfulness   Image-text-to-text   Instruct   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow   Tool-use   Vision   Vision-language-model
Model Card on HF 🤗: https://huggingface.co/Jackwang111/FaithEyes-7B-SFT 

FaithEyes 7B SFT Parameters and Internals

LLM NameFaithEyes 7B SFT
Repository 🤗https://huggingface.co/Jackwang111/FaithEyes-7B-SFT 
Base Model(s)  Qwen/Qwen2.5-VL-7B-Instruct   Qwen/Qwen2.5-VL-7B-Instruct
Model Size7b
Required VRAM16.6 GB
Updated2026-10-03
MaintainerJackwang111
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.7 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.54.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to FaithEyes 7B SFT

Best Alternatives
Context / RAM
Downloads
Likes
OmniLong Qwen2.5 VL 7B512K / 16.6 GB72
Qwen2.5 VL 7B Instruct125K / 16.7 GB87409051666
OlmOCR 2 7B 1025 FP8125K / 10 GB540426253
OlmOCR 2 7B 1025125K / 16.6 GB244728157
RolmOCR125K / 16.6 GB224280589
FaithEyes 7B RL125K / 16.6 GB260
ICM R2125K / 16.6 GB274
Qwen2.5 VL 7B Instruct FP4125K / 7.2 GB491653
SpatialBlock 7B Direct125K / 16.6 GB490
Cosmos Reason1 7B125K / 16.6 GB62913244
Note: green Score (e.g. "73.2") means that the model is better than Jackwang111/FaithEyes-7B-SFT.