Upload 8 files
Browse files- .gitattributes +1 -0
- added_tokens.json +8 -0
- config.json +43 -0
- scheduler.pt +3 -0
- special_tokens_map.json +11 -0
- tokenizer.model +3 -0
- tokenizer_config.json +72 -0
- trainer_state.json +3 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<ST_end>": 32002,
|
4 |
+
"<ST_patch>": 32000,
|
5 |
+
"<ST_start>": 32001,
|
6 |
+
"<s>": 1,
|
7 |
+
"<unk>": 0
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./base_checkpoint/vicuna-7b-v1.5-16k",
|
3 |
+
"architectures": [
|
4 |
+
"STLlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"freeze_st_mlp_adapter": false,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"lin_hidden_size": 128,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"max_sequence_length": 16384,
|
17 |
+
"model_type": "STLlama",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"num_key_value_heads": 32,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pretrain_ST_model_path": "./base_checkpoint/st_encoder/pretrain_stencoder.pth",
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": {
|
26 |
+
"factor": 4.0,
|
27 |
+
"type": "linear"
|
28 |
+
},
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sep_st_conv_front": false,
|
31 |
+
"st_hidden_size": 64,
|
32 |
+
"st_select_layer": -2,
|
33 |
+
"st_tower": "ST_Encoder",
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"time_steps": 12,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.34.0",
|
38 |
+
"tune_st_mlp_adapter": true,
|
39 |
+
"use_cache": false,
|
40 |
+
"use_st_proj": true,
|
41 |
+
"use_st_start_end": true,
|
42 |
+
"vocab_size": 32003
|
43 |
+
}
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:397633bcfd75d06bd0d2ecb3b05671d9cd68a12e70ae6966f4941a96a638fd33
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<ST_patch>",
|
4 |
+
"<ST_start>",
|
5 |
+
"<ST_end>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"pad_token": "<unk>",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
30 |
+
"content": "<ST_patch>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": true,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<ST_start>",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<ST_end>",
|
47 |
+
"lstrip": true,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<ST_patch>",
|
56 |
+
"<ST_start>",
|
57 |
+
"<ST_end>"
|
58 |
+
],
|
59 |
+
"bos_token": "<s>",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "</s>",
|
62 |
+
"legacy": false,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<unk>",
|
65 |
+
"padding_side": "right",
|
66 |
+
"sp_model_kwargs": {},
|
67 |
+
"spaces_between_special_tokens": false,
|
68 |
+
"tokenizer_class": "LlamaTokenizer",
|
69 |
+
"tokenizer_file": null,
|
70 |
+
"unk_token": "<unk>",
|
71 |
+
"use_default_system_prompt": true
|
72 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea701655fc92d0455890517494856a595eb990ed105c33505982fd441e63f40
|
3 |
+
size 11663943
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0c67b0cc5a961c6b37cfa75f778a3ffdd104a1ab4e6e16a6ae67048ff2f71c9
|
3 |
+
size 4411
|