LLM EXPLORER 66,704 MODELS INDEXED

VEHME by phuongnt

By phuongnt · 65 downloads
HF Repo ↗ Copy URL

VEHME is an open-source language model by phuongnt. Features: 7b LLM, VRAM: 16.6GB, Context: 125K, License: apache-2.0, Instruction-Based.

  Automated-grading Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-...   Conversational   En   Error-detection   Error-localization   Grpo   Handwritten-mathematics   Image-text-to-text   Instruct   Mathematical-reasoning   Qwen2.5-vl   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow   Vehme   Vision   Vision-language-model
Model Card on HF 🤗: https://huggingface.co/phuongnt/VEHME 

VEHME Parameters and Internals

LLM NameVEHME
Repository 🤗https://huggingface.co/phuongnt/VEHME 
Base Model(s)  Qwen/Qwen2.5-VL-7B-Instruct   Qwen/Qwen2.5-VL-7B-Instruct
Model Size7b
Required VRAM16.6 GB
Updated2026-11-06
Maintainerphuongnt
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 Version4.51.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to VEHME

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
ProactiveMobile Qwen2.5 VL 7B125K / 16.6 GB1152
RolmOCR125K / 16.6 GB224280589
Qwen2.5 VL 7B Instruct FP4125K / 7.2 GB491653
Back2Struct Image2SVG 7B125K / 16.6 GB472
Cosmos Reason1 7B125K / 16.6 GB62913244
FaithEyes 7B RL125K / 16.6 GB260
Note: green Score (e.g. "73.2") means that the model is better than phuongnt/VEHME.