Update README.md
Browse files
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 |
|