kepton0117 commited on
Commit
f1fe664
·
verified ·
1 Parent(s): 296a620

sn38 2018 merge

Browse files
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "NanochronoForCausalLM"
4
+ ],
5
+ "attention_multiplier": 1.2,
6
+ "aux_gate_dim": 12,
7
+ "aux_layers": [
8
+ 1,
9
+ 3,
10
+ 5,
11
+ 7,
12
+ 9,
13
+ 11,
14
+ 13,
15
+ 15,
16
+ 17,
17
+ 19,
18
+ 21,
19
+ 23,
20
+ 25,
21
+ 27
22
+ ],
23
+ "bos_token_id": 32759,
24
+ "dtype": "bfloat16",
25
+ "eos_token_id": 32763,
26
+ "final_logit_softcapping": 15.0,
27
+ "hidden_size": 1792,
28
+ "intermediate_size": 7168,
29
+ "layer_types": [
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "full_attention"
58
+ ],
59
+ "max_position_embeddings": 2048,
60
+ "mix_gate_dim": 24,
61
+ "model_type": "sn38-nanochrono",
62
+ "num_attention_heads": 14,
63
+ "num_hidden_layers": 28,
64
+ "num_key_value_heads": 14,
65
+ "pad_token_id": 32763,
66
+ "rope_theta": 100000.0,
67
+ "sliding_window": 512,
68
+ "tap_layer": 14,
69
+ "tie_word_embeddings": false,
70
+ "transformers_version": "5.16.1",
71
+ "use_cache": true,
72
+ "vocab_size": 32768
73
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 32759,
3
+ "do_sample": true,
4
+ "eos_token_id": 32763,
5
+ "max_new_tokens": 256,
6
+ "pad_token_id": 32763,
7
+ "temperature": 0.8,
8
+ "top_k": 50,
9
+ "transformers_version": "5.16.1"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b208fe1e148ee111db3f58d80b2447a6a5e3501c9c498d1fc0151de5e5248e62
3
+ size 4037045716
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|bos|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|assistant_end|>",
6
+ "is_local": true,
7
+ "local_files_only": false,
8
+ "model_max_length": 2048,
9
+ "pad_token": "<|assistant_end|>",
10
+ "tokenizer_class": "TokenizersBackend"
11
+ }