apmoore1 commited on
Commit
f2ddaee
·
verified ·
1 Parent(s): a975e55

Push model using huggingface_hub.

Browse files
Files changed (4) hide show
  1. README.md +10 -3
  2. base_model_config/config.json +47 -0
  3. config.json +11 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,10 @@
1
- ---
2
- license: cc-by-nc-sa-4.0
3
- ---
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - model_hub_mixin
4
+ - pytorch_model_hub_mixin
5
+ ---
6
+
7
+ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
8
+ - Code: [More Information Needed]
9
+ - Paper: [More Information Needed]
10
+ - Docs: [More Information Needed]
base_model_config/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "causal_mask": false,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "dtype": "float32",
17
+ "embedding_dropout": 0.0,
18
+ "eos_token_id": 50282,
19
+ "global_attn_every_n_layers": 3,
20
+ "global_rope_theta": 160000.0,
21
+ "gradient_checkpointing": false,
22
+ "hidden_activation": "gelu",
23
+ "hidden_size": 256,
24
+ "initializer_cutoff_factor": 2.0,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 384,
27
+ "is_causal": false,
28
+ "layer_norm_eps": 1e-05,
29
+ "local_attention": 128,
30
+ "local_rope_theta": 160000.0,
31
+ "max_position_embeddings": 7999,
32
+ "mlp_bias": false,
33
+ "mlp_dropout": 0.0,
34
+ "model_type": "modernbert",
35
+ "norm_bias": false,
36
+ "norm_eps": 1e-05,
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 7,
39
+ "pad_token_id": 50283,
40
+ "position_embedding_type": "sans_pos",
41
+ "repad_logits_with_grad": false,
42
+ "sep_token_id": 50282,
43
+ "sparse_pred_ignore_index": -100,
44
+ "sparse_prediction": false,
45
+ "transformers_version": "4.57.1",
46
+ "vocab_size": 50368
47
+ }
config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_scalar_mixer": false,
3
+ "base_model": null,
4
+ "base_model_name": "jhu-clsp/ettin-encoder-17m",
5
+ "batch_first": true,
6
+ "freeze_base_model": false,
7
+ "number_transformer_encoder_layers": 0,
8
+ "scalar_mix_layer_norm": true,
9
+ "transformer_encoder_hidden_dim": 512,
10
+ "transformer_encoder_num_heads": 8
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80afe087d57475f5a55b3668a037e93c5c802c6a4d281e8db0442783e481878d
3
+ size 67194384