mohammadmahdinouri commited on
Commit
d4c7544
·
verified ·
1 Parent(s): aa1cd17

Upload DistillationWrapper

Browse files
Files changed (2) hide show
  1. config.json +3 -3
  2. model.safetensors +2 -2
config.json CHANGED
@@ -8,7 +8,7 @@
8
  "dtype": "float32",
9
  "embedding_size": 128,
10
  "expert_intermediate_size": 2624,
11
- "group_depth": 4,
12
  "hidden_act": "gelu",
13
  "hidden_dropout_prob": 0.1,
14
  "hidden_size": 768,
@@ -21,13 +21,13 @@
21
  "max_position_embeddings": 8192,
22
  "model_type": "ModernALBERT",
23
  "num_attention_heads": 16,
24
- "num_expert_modules": 2,
25
  "num_experts": 8,
26
  "num_hidden_layers": 12,
27
  "pad_token_id": 0,
28
  "router_jitter_noise": 0.01,
29
  "top_k": 2,
30
- "transformers_version": "4.56.2",
31
  "use_adapter": true,
32
  "use_cache": true,
33
  "use_moa": true,
 
8
  "dtype": "float32",
9
  "embedding_size": 128,
10
  "expert_intermediate_size": 2624,
11
+ "group_depth": 3,
12
  "hidden_act": "gelu",
13
  "hidden_dropout_prob": 0.1,
14
  "hidden_size": 768,
 
21
  "max_position_embeddings": 8192,
22
  "model_type": "ModernALBERT",
23
  "num_attention_heads": 16,
24
+ "num_expert_modules": 3,
25
  "num_experts": 8,
26
  "num_hidden_layers": 12,
27
  "pad_token_id": 0,
28
  "router_jitter_noise": 0.01,
29
  "top_k": 2,
30
+ "transformers_version": "4.57.0",
31
  "use_adapter": true,
32
  "use_cache": true,
33
  "use_moa": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cc8411a24b160e69b851a7e03285c4587ddc80a4c800460e21b604330bfa66b
3
- size 128468328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1670ae18ca7a2c98399a28649b1a3a833c651819e54a64f537c4430206d6cfc
3
+ size 168188768