ReactiveAI
/

RxT-Beta-Decoder-SMAT

Text Generation

model_hub_mixin

pytorch_model_hub_mixin

🇪🇺 Region: EU

Model card Files Files and versions

AdamF92 commited on 15 days ago

Commit

0e5f840

·

verified ·

1 Parent(s): 6268fdb

Epoch 0 - Val loss 3.1529

Files changed (2) hide show

config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -32,7 +32,7 @@
     "dense",
     "moe"
   ],
-  "stm_size": 4096,
   "use_attention_output_bias": false,
   "use_flash_attention": true,
   "use_gated": true,

     "dense",
     "moe"
   ],
+  "stm_size": 8192,
   "use_attention_output_bias": false,
   "use_flash_attention": true,
   "use_gated": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6750fcb12d6eebb247fd37f3fe84957ccf72a653e3a55fbe6f241991f76f04b
 size 5772284720

 version https://git-lfs.github.com/spec/v1
+oid sha256:b14c6e8b8b8d411f719a6b488ca21dcf2b1c363f317878ce57a65b4a097f9118
 size 5772284720