rp-yu commited on
Commit
471de27
·
verified ·
1 Parent(s): 38d1185

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -16,8 +16,10 @@ base_model:
16
  - Dream-org/Dream-v0-Instruct-7B
17
  pipeline_tag: image-text-to-text
18
  ---
 
 
 
19
 
20
- # Dimple-7B 🧊
21
 
22
  **Dimple** is the first Discrete Diffusion Multimodal Large Language Model (DMLLM) that leverages a hybrid training paradigm combining autoregressive and diffusion-based instruction tuning. The model architecture is similar to Qwen and LLaVA, while introducing a novel **autoregressive-then-diffusion** training strategy:
23
 
 
16
  - Dream-org/Dream-v0-Instruct-7B
17
  pipeline_tag: image-text-to-text
18
  ---
19
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/635364b3c41f548fe39db945/T6ffjtAkFkI76QjXmN6iR.png" alt="Dimple" style="width:100%;"/>
20
+
21
+ # Dimple-7B 💧
22
 
 
23
 
24
  **Dimple** is the first Discrete Diffusion Multimodal Large Language Model (DMLLM) that leverages a hybrid training paradigm combining autoregressive and diffusion-based instruction tuning. The model architecture is similar to Qwen and LLaVA, while introducing a novel **autoregressive-then-diffusion** training strategy:
25