Upload folder using huggingface_hub

actor/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "stabilityai/japanese-stablelm-base-alpha-7b",
+  "architectures": [
+    "JapaneseStableLMAlphaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "stabilityai/japanese-stablelm-base-alpha-7b--configuration_japanese_stablelm_alpha.JapaneseStableLMAlphaConfig",
+    "AutoModelForCausalLM": "stabilityai/japanese-stablelm-base-alpha-7b--modeling_japanese_stablelm_alpha.JapaneseStableLMAlphaForCausalLM"
+  },
+  "bos_token_id": 3,
+  "classifier_dropout": 0.1,
+  "end_token_id": 3,
+  "eos_token_id": 3,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 3,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "rotary_scale_base": 512,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.3",
+  "use_bias_in_mlp": false,
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 65536
+}

actor/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578fa0ed4d6dbee435f21d7f7a741506d09cdd93cce241008abf725407cbdb41
+size 1033724

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "stabilityai/japanese-stablelm-base-alpha-7b",
+  "architectures": [
+    "JapaneseStableLMAlphaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "stabilityai/japanese-stablelm-base-alpha-7b--configuration_japanese_stablelm_alpha.JapaneseStableLMAlphaConfig",
+    "AutoModelForCausalLM": "stabilityai/japanese-stablelm-base-alpha-7b--modeling_japanese_stablelm_alpha.JapaneseStableLMAlphaForCausalLM"
+  },
+  "bos_token_id": 3,
+  "classifier_dropout": 0.1,
+  "end_token_id": 3,
+  "eos_token_id": 3,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 3,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "rotary_scale_base": 512,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.3",
+  "use_bias_in_mlp": false,
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "eos_token_id": 3,
+  "pad_token_id": 3,
+  "transformers_version": "4.33.3"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad3a5e71f32fd139d3642d6f62a465157a12aedd7d1284597f413ea9e54a9702
+size 4989354849

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f405c818e35844824a007ab0da2cb8f5e411e0b86014dd3b8b1758a17ab526
+size 4991453895

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499819afa1322f5ec4a817dfcb3b7e43d44f715d43b5eb53b4cbb77ccd69bc8f
+size 4045570255

pytorch_model.bin.index.json

@@ -0,0 +1,267 @@
+{
+  "metadata": {
+    "total_size": 11060824064
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.embed_in.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.11.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.11.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.11.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}