Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +75 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 1024,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "0\u20131000",
|
| 24 |
+
"1": "10001\u201311000",
|
| 25 |
+
"2": "1001\u20132000",
|
| 26 |
+
"3": "11001\u2013\u221e",
|
| 27 |
+
"4": "2001\u20133000",
|
| 28 |
+
"5": "3001\u20134000",
|
| 29 |
+
"6": "4001\u20135000",
|
| 30 |
+
"7": "5001\u20136000",
|
| 31 |
+
"8": "6001\u20137000",
|
| 32 |
+
"9": "7001\u20138000",
|
| 33 |
+
"10": "8001\u20139000",
|
| 34 |
+
"11": "9001\u201310000"
|
| 35 |
+
},
|
| 36 |
+
"initializer_cutoff_factor": 2.0,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 2624,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"0\u20131000": 0,
|
| 41 |
+
"10001\u201311000": 1,
|
| 42 |
+
"1001\u20132000": 2,
|
| 43 |
+
"11001\u2013\u221e": 3,
|
| 44 |
+
"2001\u20133000": 4,
|
| 45 |
+
"3001\u20134000": 5,
|
| 46 |
+
"4001\u20135000": 6,
|
| 47 |
+
"5001\u20136000": 7,
|
| 48 |
+
"6001\u20137000": 8,
|
| 49 |
+
"7001\u20138000": 9,
|
| 50 |
+
"8001\u20139000": 10,
|
| 51 |
+
"9001\u201310000": 11
|
| 52 |
+
},
|
| 53 |
+
"layer_norm_eps": 1e-05,
|
| 54 |
+
"local_attention": 128,
|
| 55 |
+
"local_rope_theta": 10000.0,
|
| 56 |
+
"max_position_embeddings": 8192,
|
| 57 |
+
"mlp_bias": false,
|
| 58 |
+
"mlp_dropout": 0.0,
|
| 59 |
+
"model_type": "modernbert",
|
| 60 |
+
"norm_bias": false,
|
| 61 |
+
"norm_eps": 1e-05,
|
| 62 |
+
"num_attention_heads": 16,
|
| 63 |
+
"num_hidden_layers": 28,
|
| 64 |
+
"pad_token_id": 50283,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"repad_logits_with_grad": false,
|
| 68 |
+
"sep_token_id": 50282,
|
| 69 |
+
"sparse_pred_ignore_index": -100,
|
| 70 |
+
"sparse_prediction": false,
|
| 71 |
+
"torch_dtype": "bfloat16",
|
| 72 |
+
"transformers_version": "4.55.4",
|
| 73 |
+
"unsloth_version": "2025.9.4",
|
| 74 |
+
"vocab_size": 50368
|
| 75 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:791e211cb43a41306794001a2c7f80aacd07cba8aa53c0768ab03905de6a1636
|
| 3 |
+
size 791705480
|