aklein4 commited on
Commit
79bc132
·
verified ·
1 Parent(s): 1630591

Upload folder using huggingface_hub

Browse files
step_000000009000/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ZebraModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": false,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "head_intermediate_size": 2560,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2560,
16
+ "latent_size": 128,
17
+ "loss_ema_beta": 0.75,
18
+ "max_position_embeddings": 8192,
19
+ "mlp_bias": false,
20
+ "model_type": "zebra",
21
+ "mu_scale": 2.0,
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 24,
24
+ "num_key_value_heads": 4,
25
+ "num_mixture_components": 8,
26
+ "pad_token_id": 0,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "rope_theta": 100000,
31
+ "tie_word_embeddings": false,
32
+ "transformers_version": "4.57.1",
33
+ "use_cache": false,
34
+ "vocab_size": 1,
35
+ "whiten_embs": true,
36
+ "z_ar_steps": 16,
37
+ "z_length": 384
38
+ }
step_000000009000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7a098874f7abd952c6a93511a86368944652b66a8a99373d93aeea26187d4b
3
+ size 2459883708