basic training

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d6f74b606411bca13942fa5ca2846eab63941cfcd80ebdd798a3c0af88ecac
+size 4982468168

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81736c8c60a45600eec755fe78f0d685569399fd48ff3d235d8d1c4b2be52fe3
+size 576934152

model.safetensors.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "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-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.29.mlp.fc2.weight": "model-00001-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.30.ln.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.31.mlp.fc2.weight": "model-00002-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"
+  }
+}