Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ license: apache-2.0
|
|
| 15 |
|
| 16 |
## Description
|
| 17 |
nanoLLaVA is a "small but mighty" 1B vision-language model designed to run efficiently on edge devices.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
| Model | **VQA v2** | **TextVQA** | **ScienceQA** | **POPE** | **MMMU (Test)** | **MMMU (Eval)** | **GQA** | **MM-VET** |
|
| 20 |
|---------|--------|---------|-----------|------|-------------|-------------|------|--------|
|
|
|
|
| 15 |
|
| 16 |
## Description
|
| 17 |
nanoLLaVA is a "small but mighty" 1B vision-language model designed to run efficiently on edge devices.
|
| 18 |
+
**Base LLM**: [Quyen-SE](https://huggingface.co/vilm/Quyen-SE) (Qwen1.5-0.5B)
|
| 19 |
+
**Vision Encoder**: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
|
| 20 |
|
| 21 |
| Model | **VQA v2** | **TextVQA** | **ScienceQA** | **POPE** | **MMMU (Test)** | **MMMU (Eval)** | **GQA** | **MM-VET** |
|
| 22 |
|---------|--------|---------|-----------|------|-------------|-------------|------|--------|
|