Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "axra/phi-2-ft",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "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": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "transformers_version": "4.38.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947538479eb99cc4f01b47ff4856ae85e6099c4deae26761b300d0bec4bee20a
+size 4982467864

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de58cf074673e4f575f2f56235a97b3599b5142e7fa11a7bb70e61d078e4a0c6
+size 576934128

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"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,340 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50296": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}