netcat420 commited on
Commit
8529e7f
·
verified ·
1 Parent(s): da7a9ed

Upload 7 files

Browse files
hierarchos_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "mode": "train",
3
+ "train": true,
4
+ "hf_dataset": "tatsu-lab/alpaca",
5
+ "hf_dataset_config": null,
6
+ "hf_dataset_split": "train",
7
+ "text_column": null,
8
+ "prompt_column": "instruction",
9
+ "completion_column": "output",
10
+ "model_path": null,
11
+ "out_dir": "./rog_ally_model",
12
+ "lora_adapter_path": null,
13
+ "tokenizer_path": null,
14
+ "resume_from_ckpt": null,
15
+ "shadow_model_path": null,
16
+ "pre_chunked_dataset": false,
17
+ "pre_pt_dataset": false,
18
+ "context_dim": 384,
19
+ "persistent_dim": 128,
20
+ "ltm_slots": 1024,
21
+ "ltm_key_dim": 128,
22
+ "ltm_val_dim": 128,
23
+ "h_hidden": 384,
24
+ "l_hidden": 384,
25
+ "h_stride": 4,
26
+ "max_h_steps": 3,
27
+ "max_l_steps": 5,
28
+ "l_conv_atol": 0.0001,
29
+ "ltm_topk": 4,
30
+ "max_length": 1512,
31
+ "auto_max_length": true,
32
+ "epochs": 30,
33
+ "batch_size": 4,
34
+ "accumulation_steps": 1,
35
+ "starting_lr": 2e-06,
36
+ "min_lr": 9e-08,
37
+ "disable_lr_schedule": false,
38
+ "ltm_lr": 0.01,
39
+ "kayla": false,
40
+ "lora_r": 8,
41
+ "lora_alpha": 16,
42
+ "finetune_unlock_percent": null,
43
+ "quantize_on_complete": false,
44
+ "grad_clip": 1.0,
45
+ "ponder_loss_weight": 0.01,
46
+ "commitment_loss_weight": 0.5,
47
+ "commitment_threshold": 0.05,
48
+ "override_scheduling": false,
49
+ "num_workers": 0,
50
+ "amp": false,
51
+ "gradient_checkpointing": false,
52
+ "compile": true,
53
+ "force_compile": true,
54
+ "debug_anomaly": false,
55
+ "max_new_tokens": 512,
56
+ "enable_quantized_learning": false,
57
+ "ltm_lora_path": null,
58
+ "device": "cpu",
59
+ "h_halt_thresh": 0.9,
60
+ "static_ltm_lr": false,
61
+ "ltm_schedule_steps": 100,
62
+ "ltm_schedule_min_lr": 1e-05,
63
+ "qtype": "INT4",
64
+ "threads": 8,
65
+ "model_type": "hierarchos",
66
+ "is_hf_dataset": true,
67
+ "vocab_size": 50257,
68
+ "completed_epoch": 60,
69
+ "tokenizer_name": "openai-community/gpt2",
70
+ "converted_from": "hierarchos_epoch_60.pt"
71
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca9b63e9024f10eff273967acc3485497e41dc3ebd04bbe6c69adfe5cebaebc
3
+ size 100403096
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff