Upload 8 files
Browse files- added_tokens.json +40 -0
- config.json +34 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257
|
40 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
3 |
+
"architectures": [
|
4 |
+
"PhiForCausalLM"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_phi.PhiConfig",
|
8 |
+
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
|
9 |
+
},
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": null,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": null,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_size": 2048,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 8192,
|
18 |
+
"layer_norm_eps": 1e-05,
|
19 |
+
"max_position_embeddings": 2048,
|
20 |
+
"model_type": "phi",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 24,
|
23 |
+
"num_key_value_heads": null,
|
24 |
+
"partial_rotary_factor": 0.5,
|
25 |
+
"qk_layernorm": false,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "float16",
|
31 |
+
"transformers_version": "4.37.0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 51200
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.37.0.dev0"
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"tokenizer_class": "CodeGenTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|