Josephgflowers
commited on
Commit
•
41fedb1
1
Parent(s):
ed70a0a
Upload 4 files
Browse files- config.json +4 -7
- special_tokens_map.json +1 -8
- tokenizer_config.json +26 -36
config.json
CHANGED
@@ -1,10 +1,8 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
@@ -17,15 +15,14 @@
|
|
17 |
"num_attention_heads": 24,
|
18 |
"num_hidden_layers": 24,
|
19 |
"num_key_value_heads": 24,
|
20 |
-
"pad_token_id":
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 10000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
-
"torch_dtype": "
|
27 |
-
"transformers_version": "4.
|
28 |
-
"unsloth_version": "2024.2",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 49216
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "MiniChat-2-DPO-3B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
|
|
15 |
"num_attention_heads": 24,
|
16 |
"num_hidden_layers": 24,
|
17 |
"num_key_value_heads": 24,
|
18 |
+
"pad_token_id": 0,
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.33.2",
|
|
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 49216
|
28 |
}
|
special_tokens_map.json
CHANGED
@@ -13,17 +13,10 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
26 |
-
"normalized":
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
}
|
|
|
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 |
}
|
tokenizer_config.json
CHANGED
@@ -1,47 +1,37 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": true,
|
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":
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
-
"stride": 0,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
-
"
|
43 |
-
|
44 |
-
|
|
|
|
|
|
|
|
|
|
|
45 |
"use_default_system_prompt": true,
|
46 |
"use_fast": true
|
47 |
}
|
|
|
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 |
+
"legacy": null,
|
22 |
+
"model_max_length": 1000000000000000019884624838656,
|
23 |
+
"pad_token": null,
|
24 |
"sp_model_kwargs": {},
|
25 |
"spaces_between_special_tokens": false,
|
|
|
26 |
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
"use_default_system_prompt": true,
|
36 |
"use_fast": true
|
37 |
}
|