Upload PhiForCausalLM

config.json

@@ -2,18 +2,23 @@
   "_name_or_path": "microsoft/phi-1_5",
   "activation_function": "gelu_new",
   "architectures": [
-    "MixFormerSequentialForCausalLM"
+    "PhiForCausalLM"
   ],
+  "attn_pdrop": 0.0,
   "auto_map": {
-    "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
-    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+    "AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
   },
   "embd_pdrop": 0.0,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
-  "model_type": "mixformer-sequential",
+  "model_type": "phi-msft",
   "n_embd": 2048,
   "n_head": 32,
+  "n_head_kv": null,
   "n_inner": null,
   "n_layer": 24,
   "n_positions": 2048,
@@ -21,6 +26,6 @@
   "rotary_dim": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.0",
+  "transformers_version": "4.36.2",
   "vocab_size": 51200
 }

generation_config.json

@@ -1,4 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.33.0"
+  "transformers_version": "4.36.2"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374337f0d32a383dcdf8f0964156aab9835a3d2a2c422cb73c51032b4e1f8974
+size 4984921688

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9e96eae3836dfcf5d1616392faef472be7ef0fadcf990958c7f64beba183f5
+size 688186984

model.safetensors.index.json

@@ -0,0 +1,252 @@
+{
+  "metadata": {
+    "total_size": 5673082880
+  },
+  "weight_map": {
+    "lm_head.linear.bias": "model-00002-of-00002.safetensors",
+    "lm_head.linear.weight": "model-00002-of-00002.safetensors",
+    "lm_head.ln.bias": "model-00002-of-00002.safetensors",
+    "lm_head.ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors"
+  }
+}