Safetensors
E1
sjain-profluent commited on
Commit
f61b414
·
verified ·
1 Parent(s): 05a2ca5

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +31 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "E1ForMaskedLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "clip_qkv": 8,
7
+ "eos_token_id": 2,
8
+ "gated_mlp": true,
9
+ "global_attention_every_n_layers": 3,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_num_positions_global": 65536,
16
+ "max_num_positions_within_seq": 8192,
17
+ "max_num_sequences": 512,
18
+ "model_type": "e1",
19
+ "no_ffn_gradient_checkpointing": true,
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 20,
22
+ "num_key_value_heads": 16,
23
+ "pad_token_id": 0,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_theta_global": 500000.0,
26
+ "rope_theta_within_seq": 10000.0,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.48.3",
30
+ "vocab_size": 34
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e20eecb66d8470fbd78b3c190b1045242541ae990f1e0e57991d83a5a5932a
3
+ size 548657620