Upload model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "data/arctrn.model",
+  "architectures": [
+    "CustomModel"
+  ],
+  "auto_map": {
+    "AutoModelForCausalLM": "modeling_custom.CustomModel"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

modeling_custom.py

@@ -0,0 +1,65 @@
+# https://huggingface.co/docs/transformers/custom_models
+
+from transformers import PreTrainedModel, GPTNeoXForCausalLM, AutoModelForCausalLM, AutoTokenizer
+from transformers.modeling_outputs import CausalLMOutputWithPast
+from torch.nn.functional import log_softmax
+from torch.nn.modules.container import ModuleList
+
+class CustomModel(PreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+
+    def forward(self, *args, labels=None, **kwargs):
+        loss = None
+        logits = None
+        for model, coeff in zip(self.models, self.coeffs):
+            logp = log_softmax(model.forward(*args, **kwargs).logits, dim=-1)
+            logits = coeff * logp if logits is None else logits + coeff * logp
+        # The rest copied from modeling_llama.py:
+        if labels is not None:
+            # Shift so that tokens < n predict n
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            # Flatten the tokens
+            loss_fct = CrossEntropyLoss()
+            shift_logits = shift_logits.view(-1, self.config.vocab_size)
+            shift_labels = shift_labels.view(-1)
+            # Enable model parallelism
+            shift_labels = shift_labels.to(shift_logits.device)
+            loss = loss_fct(shift_logits, shift_labels)
+
+        return CausalLMOutputWithPast(loss=loss, logits=logits)
+        
+
+    @classmethod
+    def combine_models(cls, *args, coeffs = [], **kwargs):
+        models = []
+        for model in args:
+            models.append(AutoModelForCausalLM.from_pretrained(model, **kwargs).eval())
+        if coeffs == []:
+            coeffs = [1/len(args)] * len(args)
+        m = cls(models[0].config)
+        m.models = ModuleList(models)
+        m.coeffs = coeffs
+        return m
+
+# In the example there is also config class but we'll just use the one from GPTNeoX
+# The norm is to import from PreTrainedModel but we'll take a shortcut
+# class CustomModel(GPTNeoXForCausalLM):
+#     def __init__(self, config):
+#         super().__init__(config)
+
+#     def forward(self, *args, **kwargs):
+#         # See https://huggingface.co/docs/transformers/main_classes/output
+#         out = super().forward(*args, **kwargs)
+#         out.logits = log_softmax(out.logits, dim=-1)
+#         return out
+
+#     @classmethod
+#     def copy_from_neox(cls, *args, **kwargs):
+#         m0 = GPTNeoXForCausalLM.from_pretrained(*args, **kwargs)
+#         m1 = cls(m0.config).to(dtype=m0.dtype, device=m0.device)
+#         m1.load_state_dict(m0.state_dict())
+#         return m1
+
+CustomModel.register_for_auto_class('AutoModelForCausalLM')

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2fc38cf2ecb181b1c94dbd9a9b9893c05a59152879d5476ced9795e78b21311
+size 9976636734

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0baa481a0303ec89e1369e32155526528fcd88865295030034450e1db3d2948
+size 9968238721

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f269cd3e13b3dc2348d49941c26375d388490244b4d4eeda52a09b56c2e4d81
+size 7009031568

pytorch_model.bin.index.json

@@ -0,0 +1,653 @@
+{
+  "metadata": {
+    "total_size": 26953678848
+  },
+  "weight_map": {
+    "models.0.lm_head.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.0.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "models.0.model.norm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "models.1.model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "models.1.model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}