squarelike commited on
Commit
b043416
1 Parent(s): e1553ef

Upload GPTNeoXForCausalLM (#1)

Browse files

- Upload GPTNeoXForCausalLM (2101d43820ac43847b4029cd71c51e4666a1281c)

Files changed (3) hide show
  1. config.json +29 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "squarelike/Gugugo-koen-1.3B-V0.9",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.5,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.31.0.dev0",
26
+ "use_cache": true,
27
+ "use_parallel_residual": true,
28
+ "vocab_size": 30080
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.31.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6582c162349238b9c01a8fbccc789caccda0ca9691548e0b208b0c0b91c6c12
3
+ size 2663730621