AdamF92 commited on
Commit
47f90e4
·
verified ·
1 Parent(s): 158763b

In progress training - batch: 4096

Browse files
Files changed (2) hide show
  1. config.json +1 -0
  2. model.safetensors +2 -2
config.json CHANGED
@@ -24,6 +24,7 @@
24
  "num_shared_experts": 2,
25
  "rope_base": 100000,
26
  "router_amp": true,
 
27
  "self_att_type": "sqa",
28
  "seq_len": 8192,
29
  "shared_expert_dim": 384,
 
24
  "num_shared_experts": 2,
25
  "rope_base": 100000,
26
  "router_amp": true,
27
+ "router_dtype": "bfloat16",
28
  "self_att_type": "sqa",
29
  "seq_len": 8192,
30
  "shared_expert_dim": 384,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1922b83261b899d56246ddde1fa99c123785097bcf83a4b2279f9b5247d7e795
3
- size 5772284720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd9df19a61a2ccba01ab8b83bcc31682a437ff1e014fae52b9fff8ea0682f67
3
+ size 5728244528