Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/data/project/private/limerobot/repos/workspace/project/llm-tf/limerobot/output/Llama-2-70b-hf/recipe21/checkpoint-390",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32000,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d93b3374b3fd73b5a5e6d9c908c3dbcf460b521013e1f55f6fad6079b791c15
+size 9852605685

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bc487a2cd80a8dcc1612fcf3da69ff698c9ec4d095f34de4597a135fdaad01
+size 9798113337

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60226ce907aac57aa45451b1c2560d4ddd85c164e2d5fe591d7c6d16fd7b0f00
+size 9965883861

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81bec465bbdf364641135962f19bdb4903f3787303fa02b81c21474e1f10ddc
+size 9798079785

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87e569dedeee91bb21a942dc00bbe3db0450cbda07f25865755a69b1c60472c
+size 9798113313

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31932baa675b2aec694339a796b54310a44f7108d11e92839d3737f157d32ce0
+size 9798113337

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed48cff7804453ec3e300e8384cbd4a4c7d8eb2c3417b9de4c75e75e811d101
+size 9965883861

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3460bdd9a8e0088c8f03e1348eee9a92e1079a41dce6246680ce1e8a7f046a23
+size 9798079785

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0d9f6378b7336e61b935df6fc6ccae4e82d8cc6bafc8393412319902a03fd5
+size 9798113313

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac949edbb87a898cd002df1abded40e857c773494d75ffab106e46888118bd1
+size 9798113337

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d216c7e3c53c774777c2bfa965471f6eef8d0f04b8ea4ea170ed5b1b42171f
+size 9965883861

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad62114eaf12675e42d2072f7c592d4c323deac2e02aa789f2d33956d2fd1b3
+size 9798079785

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d180ffb0b019f1eb51c7ea162fef673d2ea2f71548a50b145dceeaf85684bb
+size 9798113313

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a28085204ca861dad2990f7918910edb5839d61f78b4ca0df8377273f70dac
+size 9496138113

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7a2619fbfd08601ae89beff51617f788969045c56a01566b6149599ba83f8f
+size 524288938

pytorch_model.bin.index.json

@@ -0,0 +1,810 @@
+{
+  "metadata": {
+    "total_size": 137953316864
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00015.bin"
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}