Upload folder using huggingface_hub (#1)

- e43f40eb53d12e6230c33d5261ebc4b1236ece08810870fa2268258e5ea042b3 (ea6f09791bbeaa79c4b4828f334f69aa51872535)
- 87a017abc8948aa23fa89387c5458c2c9cfa5d4c98c420e8a2d12b05d0c80804 (dc5f33e35b3dd82ecba186873d5c8c492d4f7bdc)
- 879fc844da242e05b65a791fb5a028e7d33b3e0893123e42f669bc799adf6b6f (324a826b7bae1c7ae17b77e376b379cba9bd3867)
- efd049026d7ff78e5adf6fbb2c5c443c2e2b2f42936533d79413054bf5039bdc (133c7cc7fbbfff07c8e8d82e8e26163255bc9ca3)
- ac885ba845646b2cbf981ac38d2881a6b50985d9affee593921d32dfe9a15f1f (356ada0600de99a2eb5ccf540d4c06ed2deb5a75)
- c8c3ef288c356ae91947fd99dd8b06d6080cbdf8ea65da37c3dc1a04b59b9ce1 (fafd8770fd6a0c161d42c4c8bf2b68ac04b22f6d)
- 580e5613d0538b5db179d9e2dd74ce214abb5e71c231bfab20bb016490d0a625 (bd75c6ecef513d94f1aa0127ecfff3287a9ad206)
- 21be09f4ede9b8d5f30ccf269a63d8cf7bf6d546771d183e93ad55e7113f9b40 (75544f15d079797a42baf8a04871ef54d5598f50)
- bb77497385aa42d33bd1419033f4e094637d9ff7ac65540dcec34df87a7a83bd (2879aff791856e830a119abe1ec2d3f535569b39)
- 1c0f0c8e293291c45fd8c902e65f6465dc89d47b36f79d65ad78c60cb0497573 (c6af71a2b10822aafc0ddcace43041f1d3451f4c)
- 6702ab292d7139342e18bd7fcc4a91bb8edc84e9a562e097452b314bd9229e62 (b493215a008c1f789d6c010b172b43ee3d3cad28)
- eef8c72253645755e8cc008ccec07bfca70077a86a15b2772cdf34ba872122b7 (181d1151c9277ec869aa37d5d9bc130c0d1c5cd4)
- c37403202b4654ad3fb4fda0160d7350a551b2a111fa876fb57cc29bd87f9ae8 (b96adcbfd2be9ac07e30e087d53b29e6453c38ed)
- 1b622507781e35a8cd37df5fb2209ca1372daebcc88d7930a3a03a532afb2e44 (815c69ddae91a6a38108b30622aa94dd3765b329)
- 0b0e43ca63ebc2eb7c310f185932f21e4287ae7498566179240d2b28ae695a20 (6495e07361f4106775677c99d07f2db41afb5941)

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-70b-hf",
+  "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": 4096,
+  "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": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "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:dd8422aa21cd75e7e7cf55b53623f17a6936995b72ca9d61c3e31d37fae56b7a
+size 9852605685

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d264aea292787f3a9b885c0f17df5b759abcbf6814ca86561577960dbb2076
+size 9798113337

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2ed5c419763d4efcc19b8622a6493964a0be5ab0ef219cbb2f20a67d10c5a7
+size 9965883861

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb650c3890853d8ad08f5d9c8cf2b372586d4464131afde3aa100f3f81aaa1c
+size 9798079785

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2d3622b5a75c11a4263b5d9c2a47e1e9956be3f464907942267f23fa059f51
+size 9798113313

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43b3d1bfea16a6aa3ace7d19fe808f8ef493059f08b0c5dd21a4c1ecb69940b
+size 9798113337

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef461f30e3e73c85bad6baf9e61a608640cb9d780a3f781ea049e6586e664160
+size 9965883861

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42067faa8a75dee99060504728fe609ac958cfd364023d6797e06cb50d3edcd2
+size 9798079785

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7f8218bbe9fa9abad969b7ae234e696db443de07ff12a7fb0fc12106f3c0d6
+size 9798113313

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e448499cdd47922484c204a0bb682fc1e896d5d32d46816161a6e05d2b180fd
+size 9798113337

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feed7506499ba7aa9c85fd101de4a555ee8ccfc430e16a5c1e71359651e4bed0
+size 9965883861

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcf469188a2c723d635a76154db9e4c3815e8d72605c44a050beeb049d4611a
+size 9798079785

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323657f49daed945f5d7a5508f3a26a592cd69a9eee31ea49516277c11d11e2e
+size 9798113313

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307823db24bd4e989dd7932b1cadae47b21d80e748934516ff930753eec4ae6a
+size 9496138113

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b9558139334cc1ce37e3bfac264f069471726f1c9815fef9e9e1a6740c2245
+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"
+  }
+}

untitled.txt

@@ -0,0 +1,8 @@
+future = api.upload_folder(
+    folder_path="/workspace/TrueHealth-Instruct-70b",
+    repo_id="truehealth/TrueHealth-Med-Instruct-70b",
+    repo_type="model",
+    multi_commits=True,
+    multi_commits_verbose=True,
+    run_as_future=True,
+)