Model upload

README.md

@@ -0,0 +1,4 @@
+---
+pipeline_tag: text-generation
+---
+5.5 bpw exl2 quant of [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407)

config.json

@@ -0,0 +1,36 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.42.3",
+    "use_cache": true,
+    "vocab_size": 32768,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.7",
+        "bits": 5.5,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.3"
+}

model.safetensors.index.json

@@ -0,0 +1,802 @@
+{
+  "metadata": {
+    "total_size": 245220139008
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00051-of-00051.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00051.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00051.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00051.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00051.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00051.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00051.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00051.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00051.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00051.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00051.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00043-of-00051.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
+    "model.layers.80.input_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.80.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.80.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
+    "model.layers.81.input_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.k_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.o_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.q_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.81.self_attn.v_proj.weight": "model-00047-of-00051.safetensors",
+    "model.layers.82.input_layernorm.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.down_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.post_attention_layernorm.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.82.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.input_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.83.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.83.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
+    "model.layers.84.input_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.mlp.up_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.84.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.input_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.85.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.85.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
+    "model.layers.86.input_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.gate_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.86.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.input_layernorm.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.down_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.gate_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.mlp.up_proj.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.post_attention_layernorm.weight": "model-00051-of-00051.safetensors",
+    "model.layers.87.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.87.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
+    "model.norm.weight": "model-00051-of-00051.safetensors"
+  }
+}

output-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab71d0a22b7003e71dd3af8291bdab2f14c00dfc2bbac9a7574998b12dda34b1
+size 8472365008

output-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729ef1726acaac3d77d44a586d8d9170f2cfa0c02bb0c7ddd212519a8deb5f97
+size 8469846456

output-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46cc68bcedab2765d39a8fe4565beb40a9d52529bbe33738af95b2adcc06307f
+size 8543735392

output-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654c49ee57f191019cfe65f4464c3ba0b36a71b5b55af2b0d9848538482eedc1
+size 8344627660

output-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6e39c3ed5ab62e435d0ca356d4fa59872a8d80170de5cb7f410ad3f9788c75
+size 8443433528

output-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a702e09f136e0e5b3c8af7f9d308eea312ce2633681501eac219abf307daf13
+size 8331869740

output-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfce992eab5248c29114f556aa1fd505d747e115dc6437c49d2503ccdd67210
+size 8461592552

output-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7acb3b1cf00747e929740c1c2b7529d616d9d4488877dae45c2012d3db0d2cae
+size 8331284508

output-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b86e525571401275e6069b6c86656d823049d27a1b8ddfc2e254f6410d40ce7
+size 8347138232

output-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe32ff6357b364c7cea0d69e9166deeb0572bf8243ae65bb0b808ee23f99b318
+size 8547424604

output-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e02fc396c5083bd24d150e9aa839b42224fc77d377193098b93ec943e5fb8f
+size 550626496

params.json

@@ -0,0 +1,11 @@
+{
+    "dim": 12288,
+    "n_layers": 88,
+    "head_dim": 128,
+    "hidden_dim": 28672,
+    "n_heads": 96,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 32768,
+    "rope_theta": 1000000.0
+}

test.py

@@ -0,0 +1,26 @@
+import json
+from typing import Dict
+
+from safetensors.torch import load_file, save_file
+from huggingface_hub import split_torch_state_dict_into_shards
+import torch
+import os
+
+def save_state_dict(state_dict: Dict[str, torch.Tensor], save_directory: str):
+    state_dict_split = split_torch_state_dict_into_shards(state_dict, filename_pattern='consolidated{suffix}.safetensors')
+    for filename, tensors in state_dict_split.filename_to_tensors.items():
+        shard = {tensor: state_dict[tensor] for tensor in tensors}
+        print("Saving", save_directory, filename)
+        save_file(shard, os.path.join(save_directory, filename))
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        with open(os.path.join(save_directory, "consolidated.safetensors.index.json"), "w") as f:
+            f.write(json.dumps(index, indent=2))
+
+big_file = 'consolidated.safetensors'
+loaded = load_file(big_file)
+
+save_state_dict(loaded, save_directory=f'.')

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583