Hugging Face's logo

AndreaUnibo
/
NQ_JetMoE_rank_lstm_updated

Safetensors
Model card Files Community
AndreaUnibo commited on
Commit
46cf5a7
•
1 Parent(s): ffbe11a

Training in progress, step 1000

Browse files
Files changed (7) hide show
  1. adapter_config.json +72 -0
  2. adapter_model.safetensors +3 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer.json +0 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +43 -0
  7. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rank_lstm_full_trained_depth3_n2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "model.layers.1.mlp.router.layer",
24
+ "model.layers.21.self_attention.experts.router.layer",
25
+ "model.layers.20.self_attention.experts.router.layer",
26
+ "model.layers.12.self_attention.kv_proj",
27
+ "model.layers.20.self_attention.kv_proj",
28
+ "model.layers.15.self_attention.kv_proj",
29
+ "model.layers.18.self_attention.kv_proj",
30
+ "model.lstm_gates.0.transform",
31
+ "model.lstm_gates.1.transform",
32
+ "model.layers.6.self_attention.kv_proj",
33
+ "model.layers.10.self_attention.kv_proj",
34
+ "model.layers.7.self_attention.kv_proj",
35
+ "model.lstm_gates.2.transform",
36
+ "model.lstm_gates.0.input_gate",
37
+ "model.layers.2.self_attention.kv_proj",
38
+ "model.layers.20.mlp.router.layer",
39
+ "model.layers.23.self_attention.kv_proj",
40
+ "model.layers.19.mlp.router.layer",
41
+ "model.layers.16.self_attention.kv_proj",
42
+ "model.layers.4.self_attention.kv_proj",
43
+ "model.layers.1.mlp.router.perturbation",
44
+ "model.layers.19.self_attention.kv_proj",
45
+ "model.lstm_gates.0.forget_gate",
46
+ "model.layers.1.self_attention.experts.router.layer",
47
+ "model.layers.21.mlp.router.layer",
48
+ "model.layers.9.self_attention.kv_proj",
49
+ "model.lstm_gates.1.input_gate",
50
+ "model.layers.21.self_attention.kv_proj",
51
+ "model.layers.22.self_attention.kv_proj",
52
+ "model.lstm_gates.1.output_gate",
53
+ "model.layers.5.self_attention.kv_proj",
54
+ "model.layers.8.self_attention.kv_proj",
55
+ "model.layers.17.self_attention.kv_proj",
56
+ "model.layers.3.self_attention.kv_proj",
57
+ "model.layers.11.self_attention.kv_proj",
58
+ "model.lstm_gates.0.output_gate",
59
+ "model.lstm_gates.2.forget_gate",
60
+ "model.layers.0.self_attention.kv_proj",
61
+ "model.lstm_gates.1.forget_gate",
62
+ "model.layers.13.self_attention.kv_proj",
63
+ "model.lstm_gates.2.output_gate",
64
+ "model.layers.1.self_attention.kv_proj",
65
+ "model.layers.19.self_attention.experts.router.layer",
66
+ "model.layers.14.self_attention.kv_proj",
67
+ "model.lstm_gates.2.input_gate"
68
+ ],
69
+ "task_type": "CAUSAL_LM",
70
+ "use_dora": false,
71
+ "use_rslora": false
72
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb4075b535d306e8a400d40b68bf3b6b3e22322b73234231528e9abe4259573
3
+ size 6961088
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 4096,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ebb30abafb6539f25921a315acd0e5bba747b74cb94aaf246e64bc74ec71f8
3
+ size 5176