Convert model to BFloat16 and shard using SafeTensors

config.json

@@ -1,4 +1,8 @@
 {
+  "_name_or_path": "neuralmagic/Llama-2-7b-pruned70-retrained",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -18,8 +22,8 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "tokenizer_class": "LlamaTokenizerFast",
-  "transformers_version": "4.37.2",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
   "use_cache": true,
-  "vocab_size": 32000,
-  "torch_dtype": "bfloat16"
+  "vocab_size": 32000
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00006.safetensors → model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baeb20300fab8e0972db24b3d53b567170aba6ab6178cb9a0871aa58a3b3050
-size 4840431640
+oid sha256:14de06ce30ff5abb553419bddfbcf4f136bf25acdc6d4b78e81ce52153dd7b0a
+size 4938985352

model-00002-of-00006.safetensors → model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3817f91c9f327eff5b6859ec51d3068098659a1b32051d5127c0fcdd8f6c7d
-size 4857209080
+oid sha256:54099b8f1e7e8ad535877bd43c645ff6bb5ea8fecc3b56e5a50235d47e13dbb2
+size 4947390880

model-00003-of-00006.safetensors → model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42500e6de7da7b14930540f070b8dffdb0c22f387af2a7f1792be9e99b072951
-size 4857209144
+oid sha256:641b79a8e42d777edc8268dd4ce54bfc16d361b47b32294fc22e3c8ca46f0107
+size 3590488816

model-00004-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cd5c78c92f3daf76d0785e795b34b3488377046307f31371f060a5ea8cd8ebc6
-size 4857209144

model-00005-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4e6cdd3ea3935eac10493aca463d9f4e2ce20cca5b759b6e08792b3fa2d59d0d
-size 4857209144

model-00006-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3070aef48703bf9cf656b2d72f7542badbf7c5421267d93496fef31cbf49daf0
-size 2684439864

model.safetensors.index.json

@@ -1,330 +1,298 @@
 {
-    "metadata": {
-        "total_size": 26953670656
-    },
-    "weight_map": {
-        "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
-        "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
-        "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
-        "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
-        "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
-        "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
-        "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
-        "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-        "model.norm.weight": "model-00006-of-00006.safetensors",
-        "lm_head.weight": "model-00006-of-00006.safetensors"
-    }
-}
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}