Instructions to use nmndeep/CLIC-CLIPS-ViT-L-14-224-CogVLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use nmndeep/CLIC-CLIPS-ViT-L-14-224-CogVLM with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:nmndeep/CLIC-CLIPS-ViT-L-14-224-CogVLM') tokenizer = open_clip.get_tokenizer('hf-hub:nmndeep/CLIC-CLIPS-ViT-L-14-224-CogVLM') - Notebooks
- Google Colab
- Kaggle
Add model
Browse files- README.md +8 -0
- added_tokens.json +4 -0
- merges.txt +0 -0
- open_clip_config.json +50 -0
- open_clip_model.safetensors +3 -0
- open_clip_pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- clip
|
| 4 |
+
library_name: open_clip
|
| 5 |
+
pipeline_tag: zero-shot-image-classification
|
| 6 |
+
license: mit
|
| 7 |
+
---
|
| 8 |
+
# Model card for CLIC-CLIPS-ViT-L-14-224-CogVLM
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 49407,
|
| 3 |
+
"<|startoftext|>": 49406
|
| 4 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
open_clip_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_cfg": {
|
| 3 |
+
"embed_dim": 768,
|
| 4 |
+
"vision_cfg": {
|
| 5 |
+
"image_size": 224,
|
| 6 |
+
"layers": 24,
|
| 7 |
+
"width": 1024,
|
| 8 |
+
"patch_size": 14,
|
| 9 |
+
"no_ln_pre": true,
|
| 10 |
+
"pool_type": "avg",
|
| 11 |
+
"final_ln_after_pool": true,
|
| 12 |
+
"norm_kwargs": {
|
| 13 |
+
"eps": 1e-06
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"text_cfg": {
|
| 17 |
+
"context_length": 80,
|
| 18 |
+
"vocab_size": 32000,
|
| 19 |
+
"hf_tokenizer_name": "bert-base-uncased",
|
| 20 |
+
"tokenizer_kwargs": {
|
| 21 |
+
"strip_sep_token": true
|
| 22 |
+
},
|
| 23 |
+
"width": 768,
|
| 24 |
+
"heads": 12,
|
| 25 |
+
"layers": 12,
|
| 26 |
+
"pool_type": "last",
|
| 27 |
+
"no_causal_mask": true,
|
| 28 |
+
"act_kwargs": {
|
| 29 |
+
"approximate": "tanh"
|
| 30 |
+
},
|
| 31 |
+
"norm_kwargs": {
|
| 32 |
+
"eps": 1e-06
|
| 33 |
+
}
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"preprocess_cfg": {
|
| 37 |
+
"mean": [
|
| 38 |
+
0.48145466,
|
| 39 |
+
0.4578275,
|
| 40 |
+
0.40821073
|
| 41 |
+
],
|
| 42 |
+
"std": [
|
| 43 |
+
0.26862954,
|
| 44 |
+
0.26130258,
|
| 45 |
+
0.27577711
|
| 46 |
+
],
|
| 47 |
+
"interpolation": "bicubic",
|
| 48 |
+
"resize_mode": "shortest"
|
| 49 |
+
}
|
| 50 |
+
}
|
open_clip_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6842ae209f1b38750358fb0deccb9ad4c56ec6541a310476f63e2dfef378b433
|
| 3 |
+
size 1657041164
|
open_clip_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff24daf545dfa66211fd48a1c307bb426081ade1c9433b41a15c9d4c24ff941d
|
| 3 |
+
size 1657162554
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|startoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"49406": {
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"49407": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"additional_special_tokens": [],
|
| 22 |
+
"bos_token": "<|startoftext|>",
|
| 23 |
+
"clean_up_tokenization_spaces": true,
|
| 24 |
+
"do_lower_case": true,
|
| 25 |
+
"eos_token": "<|endoftext|>",
|
| 26 |
+
"errors": "replace",
|
| 27 |
+
"model_max_length": 77,
|
| 28 |
+
"pad_token": "<|endoftext|>",
|
| 29 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 30 |
+
"unk_token": "<|endoftext|>"
|
| 31 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|