Commit
•
2409bd2
1
Parent(s):
6c48727
Upload 5 files
Browse files- config.json +5 -4
- special_tokens_map.json +23 -1
- tokenizer.json +0 -0
- tokenizer_config.json +33 -1
config.json
CHANGED
@@ -1,19 +1,20 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
-
"bos_token_id":
|
7 |
-
"eos_token_id":
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
|
|
12 |
"max_sequence_length": 2048,
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
-
"pad_token_id":
|
17 |
"rms_norm_eps": 1e-06,
|
18 |
"tie_word_embeddings": false,
|
19 |
"torch_dtype": "float16",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Guanaco",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
"max_sequence_length": 2048,
|
14 |
"model_type": "llama",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
+
"pad_token_id": 0,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"tie_word_embeddings": false,
|
20 |
"torch_dtype": "float16",
|
special_tokens_map.json
CHANGED
@@ -1 +1,23 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1,33 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|