Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "</s>": 2,
+  "<madeupword0>": 256001,
+  "<madeupword1>": 256002,
+  "<madeupword2>": 256003,
+  "<madeupword3>": 256004,
+  "<madeupword4>": 256005,
+  "<madeupword5>": 256006,
+  "<madeupword6>": 256007,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--facebook--xglm-7.5B/snapshots/732d59308a844004bd9a4def972cc7c3896a38e0",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 32,
+  "bos_token_id": 0,
+  "d_model": 4096,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "xglm",
+  "num_layers": 32,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 256008
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1cbecabfc12bce6b3818ceb68e51cff3298f28b7b2d4142cfa65eb3b65eea2
+size 5453577152

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3bada0b0f6119287f228d5e9aac36f85a6de6df21f9653512073c5e28e89236
+size 5370149472

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af51d22c33f6a17559400a74a73e1ba9995a58a9d8ea1b1b4cb77c05e64efb69
+size 4161873720

model.safetensors.index.json

@@ -0,0 +1,522 @@
+{
+  "metadata": {
+    "total_size": 14985543680
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors"
+  }
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
+size 4920706

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3a00d56b48a099ef2433e8d685c3e979970beb347780b2d5c1ec7cc60f648e
+size 17210069

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256001": {
+      "content": "<madeupword0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256002": {
+      "content": "<madeupword1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256003": {
+      "content": "<madeupword2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256004": {
+      "content": "<madeupword3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256005": {
+      "content": "<madeupword4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256006": {
+      "content": "<madeupword5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256007": {
+      "content": "<madeupword6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<madeupword0>",
+    "<madeupword1>",
+    "<madeupword2>",
+    "<madeupword3>",
+    "<madeupword4>",
+    "<madeupword5>",
+    "<madeupword6>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XGLMTokenizer",
+  "unk_token": "<unk>"
+}