first commit
Browse files- .gitattributes +1 -0
- config.yaml +80 -0
- paddle_model.pdparams +3 -0
- special_tokens_map.json +23 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -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 |
+
paddle_model.pdparams filter=lfs diff=lfs merge=lfs -text
|
config.yaml
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
arch:
|
2 |
+
type: TransformerLMHeadModel
|
3 |
+
args:
|
4 |
+
transformer_config:
|
5 |
+
type: TransformerDecoderOnlyModel
|
6 |
+
args:
|
7 |
+
embed_config:
|
8 |
+
type: TransformerEmbeddingBlock
|
9 |
+
args:
|
10 |
+
token_embed_config:
|
11 |
+
type: TokenEmbedding
|
12 |
+
args:
|
13 |
+
n_embed: 2048
|
14 |
+
n_vocab: 32000
|
15 |
+
pos_embed_config: null
|
16 |
+
type_embed_config: null
|
17 |
+
ln_config: null
|
18 |
+
p_drop_embed: 0.0
|
19 |
+
concat_strategy: id_first
|
20 |
+
decoder_config:
|
21 |
+
type: TransformerDecoderBlock
|
22 |
+
args:
|
23 |
+
attn_config:
|
24 |
+
type: LlamaAttention
|
25 |
+
args:
|
26 |
+
n_embed: 2048
|
27 |
+
n_pos: 2048
|
28 |
+
n_head: 32
|
29 |
+
n_key_value_head: 4
|
30 |
+
head_size: 64
|
31 |
+
p_drop_attn: 0.0
|
32 |
+
p_drop_resid: 0.0
|
33 |
+
bias_attn: false
|
34 |
+
bias_proj: false
|
35 |
+
cross_attn: false
|
36 |
+
scale_dot_product: true
|
37 |
+
scale_layer_wise: false
|
38 |
+
layer_idx: null
|
39 |
+
rope_config:
|
40 |
+
type: RotaryPositionEmbedding
|
41 |
+
args:
|
42 |
+
head_size: 64
|
43 |
+
n_pos: 2048
|
44 |
+
base: 10000
|
45 |
+
scaling_type: null
|
46 |
+
scaling_factor: null
|
47 |
+
mlp_config:
|
48 |
+
type: LlamaMLP
|
49 |
+
args:
|
50 |
+
n_embed: 2048
|
51 |
+
n_inner: 5632
|
52 |
+
act_fn_config:
|
53 |
+
type: SiLUActivation
|
54 |
+
args: {}
|
55 |
+
ln_config:
|
56 |
+
type: LlamaRMSNorm
|
57 |
+
args:
|
58 |
+
n_embed: 2048
|
59 |
+
ln_eps: 1.0e-05
|
60 |
+
n_embed: 2048
|
61 |
+
post_norm: false
|
62 |
+
add_cross_attn: false
|
63 |
+
n_embed: 2048
|
64 |
+
n_layer: 22
|
65 |
+
n_head: 32
|
66 |
+
ln_config:
|
67 |
+
type: LlamaRMSNorm
|
68 |
+
args:
|
69 |
+
n_embed: 2048
|
70 |
+
ln_eps: 1.0e-05
|
71 |
+
perform_linear_bias: false
|
72 |
+
attn_window_size_loop_unit: null
|
73 |
+
lm_head_config:
|
74 |
+
type: TransformerLMHead
|
75 |
+
args:
|
76 |
+
n_vocab: 32000
|
77 |
+
n_embed: 2048
|
78 |
+
perform_transform: false
|
79 |
+
act_fn_config: null
|
80 |
+
ln_config: null
|
paddle_model.pdparams
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4417c90cf1767a9695f0e6a0107247795f87556a47b9dba67da4e67ac7f6bd7f
|
3 |
+
size 4400216632
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": null,
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|