Upload 12 files

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "MixFormerSequentialForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mixformer-sequential",
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.30.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f78df19fac019d9c5862f8ca3a0fdbfc96e89e34554330dadb5adbf3304d1f6
+size 1963656040

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb5bc6ca74f7f3383f5fb1bc66cb113d6e0f9717147371a58edf0b2b1222af
+size 1947036688

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1514395d1581f09ec013db88bd28b3487fb6617ee22f7a4a92ff0c816f998927
+size 1762418144

model.safetensors.index.json

@@ -0,0 +1,276 @@
+{
+  "metadata": {
+    "total_size": 5673084416
+  },
+  "weight_map": {
+    "layers.0.wte.weight": "model-00001-of-00003.safetensors",
+    "layers.1.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.1.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.1.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.10.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.10.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.10.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.10.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.11.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.11.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.11.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.11.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.12.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.12.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.12.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.12.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.13.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.13.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.13.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.13.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.14.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.14.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.14.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.14.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.15.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.15.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.15.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.15.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.16.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.16.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.16.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.16.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.17.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.17.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.17.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.17.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.18.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.18.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.18.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.18.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.18.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.19.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.19.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.19.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.19.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.19.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.19.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.19.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.2.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.2.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.2.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.20.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.20.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.20.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.20.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.21.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.21.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.21.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.21.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.22.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.22.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.22.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.22.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.23.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.23.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.23.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.23.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.24.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.24.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mixer.Wqkv.bias": "model-00003-of-00003.safetensors",
+    "layers.24.mixer.Wqkv.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mixer.out_proj.bias": "model-00003-of-00003.safetensors",
+    "layers.24.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mixer.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "layers.24.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "layers.25.linear.bias": "model-00003-of-00003.safetensors",
+    "layers.25.linear.weight": "model-00003-of-00003.safetensors",
+    "layers.25.ln.bias": "model-00003-of-00003.safetensors",
+    "layers.25.ln.weight": "model-00003-of-00003.safetensors",
+    "layers.3.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.3.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.3.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.4.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.4.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.4.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.5.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.5.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.5.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.6.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.6.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.6.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.7.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.7.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.7.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "layers.8.ln.bias": "model-00001-of-00003.safetensors",
+    "layers.8.ln.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mixer.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "layers.8.mixer.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mixer.out_proj.bias": "model-00001-of-00003.safetensors",
+    "layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mixer.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "layers.8.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "layers.9.ln.bias": "model-00002-of-00003.safetensors",
+    "layers.9.ln.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mixer.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "layers.9.mixer.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mixer.out_proj.bias": "model-00002-of-00003.safetensors",
+    "layers.9.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mixer.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.fc2.weight": "model-00002-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}