Instructions to use RISys-Lab/ReasonCLIP-B32-S1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RISys-Lab/ReasonCLIP-B32-S1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="RISys-Lab/ReasonCLIP-B32-S1") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("RISys-Lab/ReasonCLIP-B32-S1") model = AutoModelForZeroShotImageClassification.from_pretrained("RISys-Lab/ReasonCLIP-B32-S1") - Notebooks
- Google Colab
- Kaggle
Copy weights from fesvhtr/clip-r-b32-s1-run0109-853
Browse files- config.json +48 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPModel"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"hidden_act": "quick_gelu",
|
| 17 |
+
"hidden_size": 512,
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 2048,
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 77,
|
| 23 |
+
"model_type": "clip_text_model",
|
| 24 |
+
"num_attention_heads": 8,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"projection_dim": 512,
|
| 27 |
+
"vocab_size": 49408
|
| 28 |
+
},
|
| 29 |
+
"transformers_version": "4.56.2",
|
| 30 |
+
"vision_config": {
|
| 31 |
+
"attention_dropout": 0.0,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dtype": "bfloat16",
|
| 34 |
+
"hidden_act": "quick_gelu",
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_factor": 1.0,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 3072,
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"model_type": "clip_vision_model",
|
| 42 |
+
"num_attention_heads": 12,
|
| 43 |
+
"num_channels": 3,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"patch_size": 32,
|
| 46 |
+
"projection_dim": 512
|
| 47 |
+
}
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a98707fc4816d9561b7b6214a6614b9c7a7d3de1edf1555b91d952a0bbdb8e2
|
| 3 |
+
size 302602194
|