Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "v000000/NM-12B-Lyris-dev-2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49eb732a555d0b442fa7b5497efa8238e0162d442599ac593c5dd2ebe59fce0
+size 1992316520

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150fa8d424310b1568a37b8052ef2e49b195657911f367e14166302272d7c8c4
+size 1929444600

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533ea5d017c744b1849205c3be3a6d7b01b7b454bb7ae927d842c4d1ec8949ef
+size 1887522624

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad31def6b9149823255cd3f8a71f56d7853762405e72c633fdc484db5f6bb18a
+size 1929444616

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c8bd3075e6ebde46abc1d2543958e5ee1dd14dbacb1799878cee2063865783
+size 1887522656

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92698480005a9663359951bd4119a698ae8ffdb5ad0ebe90a8011e71522a34ec
+size 1929444632

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447014adbc6d9a1613893fb3592b412bd99437d527411bd375f3ce46a5570f0f
+size 1887522656

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5670fcf130f9201590ccfe21f1c0a7092cbaf15576ad1bb3ad91c51fcf7140
+size 1929444632

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4d294f80e33e2e2a15c6ed1d8b950da1e9522aaad5b87c140e68df4af0188b
+size 1887522656

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109dbed6190c7506f536c2111fe4c46b5a55ba0742c9dc5a36a2444c532dd7c2
+size 1929444632

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b861bb2388cd3acdd69ec7a3e6254204d2f3b827861ff545905e89afbf470af4
+size 1887522656

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa315a892c0979ed404caee529a62c9b0201d1b6dbde612d1e39917b9e1c56e
+size 1929444632

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a696a14be686e64f8c84f2917a4bdff494fe629b697a8285df1e5ac08c30c4f3
+size 1489009208

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.norm.weight": "model-00013-of-00013.safetensors"
+  }
+}