CamDistill-8B

Camera-movement distillation SFT model, based on Qwen/Qwen3-VL-8B-Instruct.

Checkpoint: v5-20260724-054032 / checkpoint-1326
Training framework: ms-swift
CamDistill config: DEPTH=6, EXTRACT_LAYERS=1,3,5,9,11,13, LAMBDA=0.05

Usage

from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained("ddz16/CamDistill-8B", torch_dtype="bfloat16", device_map="auto")
processor = AutoProcessor.from_pretrained("ddz16/CamDistill-8B")

Downloads last month: 34

Safetensors

Model size

9B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ddz16/CamDistill-8B

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(437)

this model