Adding {"trust_remote_code": true} to config.json
Browse files- config.json +67 -66
config.json
CHANGED
@@ -1,66 +1,67 @@
|
|
1 |
-
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"
|
7 |
-
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
|
12 |
-
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
|
25 |
-
"retrieval.
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
|
30 |
-
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
|
53 |
-
"
|
54 |
-
"retrieval.
|
55 |
-
"
|
56 |
-
"
|
57 |
-
|
58 |
-
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
|
|
|
|
1 |
+
{
|
2 |
+
"trust_remote_code": true,
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaLoRA"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "jinaai/xlm-roberta-flash-implementation--configuration_xlm_roberta.XLMRobertaFlashConfig",
|
9 |
+
"AutoModel": "jinaai/xlm-roberta-flash-implementation--modeling_lora.XLMRobertaLoRA",
|
10 |
+
"AutoModelForMaskedLM": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForMaskedLM",
|
11 |
+
"AutoModelForPreTraining": "jinaai/xlm-roberta-flash-implementation--modeling_xlm_roberta.XLMRobertaForPreTraining"
|
12 |
+
},
|
13 |
+
"bos_token_id": 0,
|
14 |
+
"classifier_dropout": null,
|
15 |
+
"emb_pooler": null,
|
16 |
+
"eos_token_id": 2,
|
17 |
+
"hidden_act": "gelu",
|
18 |
+
"hidden_dropout_prob": 0.1,
|
19 |
+
"hidden_size": 1024,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
+
"layer_norm_eps": 1e-05,
|
23 |
+
"load_trained_adapters": true,
|
24 |
+
"lora_adaptations": [
|
25 |
+
"retrieval.query",
|
26 |
+
"retrieval.passage",
|
27 |
+
"separation",
|
28 |
+
"classification",
|
29 |
+
"text-matching"
|
30 |
+
],
|
31 |
+
"lora_alpha": 1,
|
32 |
+
"lora_dropout_p": 0.0,
|
33 |
+
"lora_main_params_trainable": false,
|
34 |
+
"lora_rank": 4,
|
35 |
+
"matryoshka_dimensions": [
|
36 |
+
32,
|
37 |
+
64,
|
38 |
+
128,
|
39 |
+
256,
|
40 |
+
512,
|
41 |
+
768,
|
42 |
+
1024
|
43 |
+
],
|
44 |
+
"max_position_embeddings": 8194,
|
45 |
+
"model_type": "xlm-roberta",
|
46 |
+
"num_attention_heads": 16,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"output_past": true,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"position_embedding_type": "rotary",
|
51 |
+
"rotary_emb_base": 20000.0,
|
52 |
+
"task_instructions": {
|
53 |
+
"classification": "",
|
54 |
+
"retrieval.passage": "Represent the document for retrieval: ",
|
55 |
+
"retrieval.query": "Represent the query for retrieving evidence documents: ",
|
56 |
+
"separation": "",
|
57 |
+
"text-matching": ""
|
58 |
+
},
|
59 |
+
"torch_dtype": "bfloat16",
|
60 |
+
"transformers_version": "4.50.0",
|
61 |
+
"truncate_dim": null,
|
62 |
+
"type_vocab_size": 1,
|
63 |
+
"use_cache": true,
|
64 |
+
"use_flash_attn": true,
|
65 |
+
"use_reentrant": false,
|
66 |
+
"vocab_size": 250002
|
67 |
+
}
|