Upload folder using huggingface_hub
Browse files- checkpoint-6000/config.json +47 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/pytorch_model.bin +3 -0
- checkpoint-6000/rng_state_0.pth +3 -0
- checkpoint-6000/rng_state_1.pth +3 -0
- checkpoint-6000/rng_state_2.pth +3 -0
- checkpoint-6000/rng_state_3.pth +3 -0
- checkpoint-6000/rng_state_4.pth +3 -0
- checkpoint-6000/rng_state_5.pth +3 -0
- checkpoint-6000/rng_state_6.pth +3 -0
- checkpoint-6000/rng_state_7.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/special_tokens_map.json +9 -0
- checkpoint-6000/tokenizer_config.json +65 -0
- checkpoint-6000/trainer_state.json +0 -0
- checkpoint-6000/training_args.bin +3 -0
checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CaduceusForMaskedLMCompat"
|
| 4 |
+
],
|
| 5 |
+
"bidirectional": true,
|
| 6 |
+
"bidirectional_strategy": "add",
|
| 7 |
+
"bidirectional_weight_tie": true,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"cls_token_id": 0,
|
| 10 |
+
"complement_map": null,
|
| 11 |
+
"d_model": 256,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"fused_add_norm": true,
|
| 15 |
+
"initializer_cfg": {
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"n_residuals_per_layer": 1,
|
| 18 |
+
"rescale_prenorm_residual": true
|
| 19 |
+
},
|
| 20 |
+
"mask_token_id": 3,
|
| 21 |
+
"model_type": "caduceus",
|
| 22 |
+
"n_layer": 16,
|
| 23 |
+
"norm_epsilon": 1e-05,
|
| 24 |
+
"pad_token_id": 4,
|
| 25 |
+
"pad_vocab_size_multiple": 8,
|
| 26 |
+
"rcps": false,
|
| 27 |
+
"residual_in_fp32": true,
|
| 28 |
+
"rms_norm": true,
|
| 29 |
+
"sep_token_id": 1,
|
| 30 |
+
"ssm_cfg": {
|
| 31 |
+
"bias": false,
|
| 32 |
+
"conv_bias": true,
|
| 33 |
+
"d_conv": 4,
|
| 34 |
+
"d_state": 16,
|
| 35 |
+
"dt_init": "random",
|
| 36 |
+
"dt_init_floor": 0.0001,
|
| 37 |
+
"dt_max": 0.1,
|
| 38 |
+
"dt_min": 0.001,
|
| 39 |
+
"dt_rank": "auto",
|
| 40 |
+
"dt_scale": 1.0,
|
| 41 |
+
"expand": 2,
|
| 42 |
+
"use_fast_path": true
|
| 43 |
+
},
|
| 44 |
+
"transformers_version": "4.57.1",
|
| 45 |
+
"unk_token_id": 6,
|
| 46 |
+
"vocab_size": 16
|
| 47 |
+
}
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da9fb4d8cc24fe4b317d029482e12488131a92f9645f394266b716cb575d4a31
|
| 3 |
+
size 62036043
|
checkpoint-6000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d41fe3ec34f43f79768b0883635f3e93b0de421bd89ce054f951db33d5d05361
|
| 3 |
+
size 31002667
|
checkpoint-6000/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cddc2b4f381e5ca5a26121bb07a893055ef5cb7d28c6c804c54b7e8d98446e73
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e223bd10aee24162e1caff1370d9823c6846b6780971014a5c65007329cf694
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d892b976cfbd46eba059246c19b4b236eef8897d221e63ff755314090b6c1468
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f995e14936a94c2b4f46193c32d32ed9c674ebe0820b87e0fe38a3f656d62bc5
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcace709c04c0017b85531964b5aaa9354a122d1139a4cd86c4acf898c0b809b
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e2a0607eaf41f26d8178eb478ff007b4207bfc0f4f183d56c62f253f2884a1f
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aafdec9b603fbcd684a36f5e84626b08d6551bd21559c78bb5220f60b0350c00
|
| 3 |
+
size 16389
|
checkpoint-6000/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e18e31b5a24e2da5e88b055997bdbce1d4a5b1ca620f28fcbe635ad6bb3da0f
|
| 3 |
+
size 16389
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48432dd5f03651c681e4075dc825970301a9afd4c065695b4976c7250819bbac
|
| 3 |
+
size 1465
|
checkpoint-6000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[BOS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
checkpoint-6000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[CLS]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[SEP]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "[BOS]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "[MASK]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "[PAD]",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"6": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
"bos_token": "[BOS]",
|
| 54 |
+
"clean_up_tokenization_spaces": false,
|
| 55 |
+
"cls_token": "[CLS]",
|
| 56 |
+
"eos_token": "[SEP]",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "[MASK]",
|
| 59 |
+
"model_max_length": 12800,
|
| 60 |
+
"pad_token": "[PAD]",
|
| 61 |
+
"padding_side": "left",
|
| 62 |
+
"sep_token": "[SEP]",
|
| 63 |
+
"tokenizer_class": "CaduceusTokenizer",
|
| 64 |
+
"unk_token": "[UNK]"
|
| 65 |
+
}
|
checkpoint-6000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02705d1deb3c1930c112fff42875a44d1c1d8e14f98c3feeda1f7c13721653ae
|
| 3 |
+
size 6033
|