Hugging Face's logo

Ostixe360
/
MoMv5-bf16

Text Generation
Transformers
Safetensors
English
Mixture of Experts
moah
mod
mh-moe
Inference Endpoints
Model card Files Community
Ostixe360 commited on
Commit
fba518c
•
1 Parent(s): be69228

Upload AnemoneForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +2 -2
  2. model.safetensors +2 -2
config.json CHANGED
@@ -16,9 +16,9 @@
16
  "expert_layer_period": 2,
17
  "expert_num_heads": 4,
18
  "hidden_act": "silu",
19
- "hidden_size": 1024,
20
  "initializer_range": 0.02,
21
- "intermediate_size": 10000,
22
  "mamba_conv_bias": true,
23
  "mamba_d_conv": 4,
24
  "mamba_d_state": 16,
 
16
  "expert_layer_period": 2,
17
  "expert_num_heads": 4,
18
  "hidden_act": "silu",
19
+ "hidden_size": 2240,
20
  "initializer_range": 0.02,
21
+ "intermediate_size": 1500,
22
  "mamba_conv_bias": true,
23
  "mamba_d_conv": 4,
24
  "mamba_d_state": 16,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca4b9d41b1999fce888605dbe976fea9d001366f4cca95f3dcc590a4e652a1aa
3
- size 1802772328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc9e3adfee95cf8b4d55586294a41708080090f998b3ad1d6dacd0f4a272716
3
+ size 2105562712