Upload 15 files

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "D:/HuggingFaceModelDownloader/Storage/timdettmers_guanaco-33b-merged",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6656,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 52,
+  "num_hidden_layers": 60,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

llama_rope_scaled_monkey_patch_16k.py

@@ -0,0 +1,65 @@
+"""Scaled Rotary Embedding module patch. Credit https://kaiokendev.github.io/til#extending-context-to-8k"""
+import torch
+import transformers
+import transformers.models.llama.modeling_llama
+from einops import rearrange
+import random
+
+
+class ScaledRotaryEmbedding(torch.nn.Module):
+    def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None):
+        super().__init__()
+        inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim))
+        self.register_buffer("inv_freq", inv_freq)
+        max_position_embeddings = 16384
+
+        # Build here to make `torch.jit.trace` work.
+        self.max_seq_len_cached = max_position_embeddings
+        t = torch.arange(
+            self.max_seq_len_cached,
+            device=self.inv_freq.device,
+            dtype=self.inv_freq.dtype,
+        )
+
+        self.scale = 1 / 8
+        t *= self.scale
+
+        freqs = torch.einsum("i,j->ij", t, self.inv_freq)
+        # Different from paper, but it uses a different permutation in order to obtain the same calculation
+        emb = torch.cat((freqs, freqs), dim=-1)
+        self.register_buffer(
+            "cos_cached", emb.cos()[None, None, :, :], persistent=False
+        )
+        self.register_buffer(
+            "sin_cached", emb.sin()[None, None, :, :], persistent=False
+        )
+
+    def forward(self, x, seq_len=None):
+        # x: [bs, num_attention_heads, seq_len, head_size]
+        # This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case.
+        if seq_len > self.max_seq_len_cached:
+            self.max_seq_len_cached = seq_len
+            t = torch.arange(
+                self.max_seq_len_cached, device=x.device, dtype=self.inv_freq.dtype
+            )
+            t *= self.scale
+            freqs = torch.einsum("i,j->ij", t, self.inv_freq)
+            # Different from paper, but it uses a different permutation in order to obtain the same calculation
+            emb = torch.cat((freqs, freqs), dim=-1).to(x.device)
+            self.register_buffer(
+                "cos_cached", emb.cos()[None, None, :, :], persistent=False
+            )
+            self.register_buffer(
+                "sin_cached", emb.sin()[None, None, :, :], persistent=False
+            )
+        return (
+            self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
+            self.sin_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
+        )
+
+
+def replace_llama_rope_with_scaled_rope():
+    print("replacing rotary embeddings with scaled equivalent")
+    transformers.models.llama.modeling_llama.LlamaRotaryEmbedding = (
+        ScaledRotaryEmbedding
+    )

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566af4fcc0352209750deffe574e014de4bd3940971cf80a1f4598cc7de3b696
+size 9818325114

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aec61ed84cd3456d4969b33955d0c6b28495c2ec62f88aa330a92583de2b23d
+size 9958103230

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4aa387437de5205f60599aca2657c2a117971ba71ce20b802037bc80c8617b
+size 9896735202

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30114cac16436b853fb23b6822b50b00808f298016f00a5b943806cfd9cd181
+size 9869470968

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945c9f9e74d7135ea45d2c93705680226260b8808d96d7dbbc8705ca6fc73427
+size 9869470932

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c767eecf976258ff12493d439d5252b087625d854f9991b0a06256e31ab41cf0
+size 9958103230

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93856d664e946ed22c2a08cd92127e90cd02fcd6fff5cfdce21ed361e5cf9d3a
+size 5687903768

pytorch_model.bin.index.json

@@ -0,0 +1,610 @@
+{
+  "metadata": {
+    "total_size": 65057902592
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": "<s>",
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}