GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
phucdu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
phucdu
Model Tree
Qwen/Qwen2.5-VL-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model utilizes Parameter-Efficient Fine-Tuning (PEFT) via LoRA and 4-bit quantization to adapt the base Qwen2.5-VL-3B-Instruct model for highly accurate text recognition from images. It achieves significant improvements in Character Error Rate (CER) and Exact Match accuracy compared to the base model.
Extracting and reading text from images (Optical Character Recognition - OCR). It is particularly tuned on single-word crops but generalizes well to standard text reading tasks.
(Mục này đã được để trống theo yêu cầu của tác giả - Không chứa code tải mô hình).
A subset of priyank-m/MJSynth_text_recognition.
down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_projComparing Base Model vs. Fine-tuned Model on the test set:
The LoRA fine-tuning process significantly enhanced the model's OCR capabilities on the target dataset, bringing the exact match accuracy up to over 85% while massively dropping both CER and WER.