Training in progress, step 500
Browse files- added_tokens.json +3 -0
- config.json +33 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +53 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 84608
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "OrionStarAI/Orion-14B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"OrionForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "OrionStarAI/Orion-14B-Chat--configuration_orion.OrionConfig",
|
9 |
+
"AutoModelForCausalLM": "OrionStarAI/Orion-14B-Chat--modeling_orion.OrionForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 1,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 5120,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 15360,
|
17 |
+
"max_position_embeddings": 4096,
|
18 |
+
"max_sequence_length": 4096,
|
19 |
+
"model_type": "orion",
|
20 |
+
"num_attention_heads": 40,
|
21 |
+
"num_hidden_layers": 40,
|
22 |
+
"num_key_value_heads": 40,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"pretraining_tp": 1,
|
25 |
+
"rms_norm_eps": 1e-05,
|
26 |
+
"rope_scaling": null,
|
27 |
+
"rope_theta": 10000.0,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.36.0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 84608
|
33 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
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": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ded43118b7418f56db97a4eed08a5c265c03120158229ddd4fbcc9658241d5f0
|
3 |
+
size 1520600
|
tokenizer_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
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 |
+
"84608": {
|
30 |
+
"content": "[PAD]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"auto_map": {
|
39 |
+
"AutoTokenizer": [
|
40 |
+
"OrionStarAI/Orion-14B-Chat--tokenization_orion.OrionTokenizer",
|
41 |
+
null
|
42 |
+
]
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"chat_template": "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\n\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"model_max_length": 4096,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sp_model_kwargs": {},
|
51 |
+
"tokenizer_class": "OrionTokenizer",
|
52 |
+
"unk_token": "<unk>"
|
53 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35ca213fe1b9824c1db2358afd22a697d1da2689ddd45a5987e0ca982f362255
|
3 |
+
size 5048
|