stacking-babylm-2025
/

Gradual_Stacking_456

Model card Files Files and versions

cordschmidt commited on Mar 23

Commit

ee18b36

·

verified ·

1 Parent(s): bd723af

Training in progress, step 7512

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 16,
-  "num_hidden_layers": 6,
   "num_key_value_heads": 16,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 16,
+  "num_hidden_layers": 12,
   "num_key_value_heads": 16,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647f01774aebf1400446088f26ec04e4b9b1962713a390f4d2f2686a25e89fc1
-size 26785216

 version https://git-lfs.github.com/spec/v1
+oid sha256:47220a4382396aedcf8db6f733cf9d4856a9acce793a24489b3f1b86872378d4
+size 47277704