Train commited on
Commit
ba7b850
·
verified ·
1 Parent(s): 374d0c7

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HumanVForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "float32",
8
+ "head_dim": 32,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 160,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 640,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention"
22
+ ],
23
+ "max_position_embeddings": 1024,
24
+ "mlp_bias": false,
25
+ "model_type": "humanv",
26
+ "num_attention_heads": 5,
27
+ "num_hidden_layers": 8,
28
+ "num_key_value_heads": 5,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_parameters": {
31
+ "rope_theta": 10000.0,
32
+ "rope_type": "default"
33
+ },
34
+ "transformers_version": "5.0.0.dev0",
35
+ "use_cache": false,
36
+ "vocab_size": 50257
37
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "5.0.0.dev0",
4
+ "use_cache": false
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f76c6649eb78ed56f780f67ed3a2a47f3cde4a91ace9233307dd04c69da578
3
+ size 77455176
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1000000000,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78053947cc47cb42fbb91144917691510c943a7a1e27d8f45bdbdeb4e2c073b1
3
+ size 5073
vocab.json ADDED
The diff for this file is too large to render. See raw diff