Upload XLMRobertaLoRA
Browse files- config.json +66 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaLoRA"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig",
|
| 8 |
+
"AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_lora.XLMRobertaLoRA",
|
| 9 |
+
"AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM",
|
| 10 |
+
"AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"emb_pooler": null,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.1,
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 4096,
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"load_trained_adapters": true,
|
| 23 |
+
"lora_adaptations": [
|
| 24 |
+
"retrieval.query",
|
| 25 |
+
"retrieval.passage",
|
| 26 |
+
"separation",
|
| 27 |
+
"classification",
|
| 28 |
+
"text-matching"
|
| 29 |
+
],
|
| 30 |
+
"lora_alpha": 1,
|
| 31 |
+
"lora_dropout_p": 0.0,
|
| 32 |
+
"lora_main_params_trainable": false,
|
| 33 |
+
"lora_rank": 4,
|
| 34 |
+
"matryoshka_dimensions": [
|
| 35 |
+
32,
|
| 36 |
+
64,
|
| 37 |
+
128,
|
| 38 |
+
256,
|
| 39 |
+
512,
|
| 40 |
+
768,
|
| 41 |
+
1024
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 8194,
|
| 44 |
+
"model_type": "xlm-roberta",
|
| 45 |
+
"num_attention_heads": 16,
|
| 46 |
+
"num_hidden_layers": 24,
|
| 47 |
+
"output_past": true,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"position_embedding_type": "rotary",
|
| 50 |
+
"rotary_emb_base": 20000.0,
|
| 51 |
+
"task_instructions": {
|
| 52 |
+
"classification": "",
|
| 53 |
+
"retrieval.passage": "Represent the document for retrieval: ",
|
| 54 |
+
"retrieval.query": "Represent the query for retrieving evidence documents: ",
|
| 55 |
+
"separation": "",
|
| 56 |
+
"text-matching": ""
|
| 57 |
+
},
|
| 58 |
+
"torch_dtype": "bfloat16",
|
| 59 |
+
"transformers_version": "4.50.0",
|
| 60 |
+
"truncate_dim": null,
|
| 61 |
+
"type_vocab_size": 1,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"use_flash_attn": true,
|
| 64 |
+
"use_reentrant": false,
|
| 65 |
+
"vocab_size": 250002
|
| 66 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17ca06efd886a065d0081912b04c9e27ef5086a9dd09659cce32aa9c84587f23
|
| 3 |
+
size 1144685320
|