Text-to-Image
MLX
Safetensors
lance
multimodal
apple-silicon
image-generation
video-generation
diffusion
flow-matching
Mixture of Experts
qwen2_5_vl
wan
port
Instructions to use RockTalk/Lance-3B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use RockTalk/Lance-3B-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Lance-3B-MLX RockTalk/Lance-3B-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add ViT config
Browse files- vit_config.json +21 -0
vit_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation": "flash_attention_2",
|
| 3 |
+
"depth": 32,
|
| 4 |
+
"fullatt_block_indexes": [7, 15, 23, 31],
|
| 5 |
+
"hidden_act": "silu",
|
| 6 |
+
"hidden_size": 1280,
|
| 7 |
+
"in_channels": 3,
|
| 8 |
+
"in_chans": 3,
|
| 9 |
+
"intermediate_size": 3420,
|
| 10 |
+
"model_type": "qwen2_5_vl",
|
| 11 |
+
"num_heads": 16,
|
| 12 |
+
"out_hidden_size": 2048,
|
| 13 |
+
"patch_size": 14,
|
| 14 |
+
"spatial_merge_size": 2,
|
| 15 |
+
"spatial_patch_size": 14,
|
| 16 |
+
"temporal_patch_size": 2,
|
| 17 |
+
"tokens_per_second": 2,
|
| 18 |
+
"torch_dtype": "bfloat16",
|
| 19 |
+
"transformers_version": "4.49.0",
|
| 20 |
+
"window_size": 112
|
| 21 |
+
}
|