Upload JargonForMaskedLM
Browse files- config.json +64 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jargon-legal-4096",
|
| 3 |
+
"activation": "relu",
|
| 4 |
+
"add_bias_kv": false,
|
| 5 |
+
"add_pooling_layer": false,
|
| 6 |
+
"add_zero_attn": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"JargonForMaskedLM"
|
| 9 |
+
],
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"auto_map": {
|
| 12 |
+
"AutoConfig": "jargon_configuration.JargonConfig",
|
| 13 |
+
"AutoModel": "jargon_model.JargonModel",
|
| 14 |
+
"AutoModelForMaskedLM": "jargon_model.JargonForMaskedLM",
|
| 15 |
+
"AutoModelForSequenceClassification": "jargon_model.JargonForSequenceClassification",
|
| 16 |
+
"AutoModelForTokenClassification": "jargon_model.JargonForTokenClassification"
|
| 17 |
+
},
|
| 18 |
+
"bias": true,
|
| 19 |
+
"bos_token_id": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"compress_layer": 1,
|
| 22 |
+
"compressed": 16,
|
| 23 |
+
"dim_feedforward": 4096,
|
| 24 |
+
"dropout": 0.1,
|
| 25 |
+
"embed_dim": 768,
|
| 26 |
+
"encoder_attention_heads": 12,
|
| 27 |
+
"encoder_decoder_attention": false,
|
| 28 |
+
"encoder_embed_dim": 768,
|
| 29 |
+
"encoder_ffn_embed_dim": 4096,
|
| 30 |
+
"encoder_normalize_before": true,
|
| 31 |
+
"eos_token_id": 2,
|
| 32 |
+
"freeze_compress": 0,
|
| 33 |
+
"hidden_act": "gelu",
|
| 34 |
+
"hidden_dropout_prob": 0.1,
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_act_fn": "gelu",
|
| 38 |
+
"intermediate_size": 4096,
|
| 39 |
+
"layer_norm_eps": 1e-05,
|
| 40 |
+
"layernorm_embedding": false,
|
| 41 |
+
"max_position_embeddings": 4098,
|
| 42 |
+
"max_positions": 4096,
|
| 43 |
+
"model_type": "jargon",
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_heads": 16,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"num_layers": 12,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"position_embedding_type": "learned",
|
| 50 |
+
"q_noise": 0,
|
| 51 |
+
"qn_block_size": 8,
|
| 52 |
+
"quant_noise_pq": 0.0,
|
| 53 |
+
"quant_noise_pq_block_size": 8,
|
| 54 |
+
"quant_noise_scalar": 0,
|
| 55 |
+
"self_attention": true,
|
| 56 |
+
"shared_kv_compressed": 1,
|
| 57 |
+
"shared_layer_kv_compressed": 1,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.31.0",
|
| 60 |
+
"type_vocab_size": 2,
|
| 61 |
+
"untie_weights_roberta": false,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 50000
|
| 64 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0248c8d7d1f41cf339fc1b91c80eba093e77da61647df7c72922838dcece276b
|
| 3 |
+
size 596809805
|