Upload NemotronForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/ckpts/nemotron/nemotron3-8b-base-hf",
+  "_name_or_path": "/ckpts/nemotron/nemotron3-8b-hf",
   "architectures": [
     "NemotronForCausalLM"
   ],
@@ -9,17 +9,15 @@
   "eos_token_id": 3,
   "hidden_act": "relu2",
   "hidden_size": 4096,
-  "initializer_range": 0.02,
+  "initializer_range": 0.01,
   "intermediate_size": 16384,
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "nemotron",
   "norm_eps": 1e-05,
-  "normalization": "layernorm1p",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "pretraining_tp": 1,
   "rope_percent": 0.5,
   "rope_percentage": 0.5,
   "rope_scaling": null,

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6eaa58031404e71c43386c2cf07cc620b84216c0bf192f7875be6e6d6f7a16d
-size 4983071064
+oid sha256:60c18eb1587e4681f0b5d2239a45b534ebab9110a358c03b6e599f4a01f24509
+size 4983070984

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61c7d16b2b6baffc7f1e14a46fa1c5650109ae7daff2caee35f07cd23c4401c
-size 4899354576
+oid sha256:bb3708b99f2136d9b1d5c8b6b68b2eca09596424f3e23157ca7939eca3983bba
+size 4899354432

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbedd282636f9a00ef30b4f58c72a5b0e79c6bfe139313ff0ff529bacd48878
-size 4966463352
+oid sha256:b20bc6b50da983e58da0481b2e4f85d66a3ee8fd37966ef6d93012d3c164fa05
+size 4966463208

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3467451be4040de8e73846fa2c725d6a4ed9948f9f7f0368c8b0ad4f76674ca4
-size 2231419784
+oid sha256:1b127cc8a0b30ac146ad442b0282a6ebd744704c9c3da502041dcc955306d8df
+size 2231419768

model.safetensors.index.json

@@ -5,327 +5,327 @@
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.10.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.23.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.30.input_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.ln.bias": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.ln.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.ln.bias": "model-00004-of-00004.safetensors",
-    "model.layers.31.input_layernorm.ln.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.ln.bias": "model-00004-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.ln.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.ln.bias": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.ln.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.input_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.input_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.ln.bias": "model-00002-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.ln.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.ln.bias": "model-00004-of-00004.safetensors",
-    "model.norm.ln.weight": "model-00004-of-00004.safetensors"
+    "model.norm.bias": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }