diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..bc5f30d6632ac0efdc7be2e9095e9e9579af2e33
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c31a96f99307dc7c9adaa497c9b5fcf52599d746
--- /dev/null
+++ b/config.json
@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "./models/m1",
+  "architectures": [
+    "AutoModelForCausalLMWithRM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "hf_utils.RewardModelConfig",
+    "AutoModel": "hf_utils.AutoModelForCausalLMWithRM"
+  },
+  "base_config": {
+    "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "bos_token_id": 128000,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "hidden_size": 8192,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "vocab_size": 128257
+  },
+  "base_model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+  "bias": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "pairwise_rm",
+  "n_labels": 1,
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "p_dropout": 0.0,
+  "pretrain_cfg": {
+    "attn_implementation": "flash_attention_2",
+    "load_in_8bit": false,
+    "token": true,
+    "trust_remote_code": true
+  },
+  "pretrained": false,
+  "pretraining_tp": 1,
+  "return_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 128257
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..0484b997a9ea9b5b6d711db644716bfd32d5470e
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}
diff --git a/hf_utils.py b/hf_utils.py
new file mode 100644
index 0000000000000000000000000000000000000000..4820bf68a9f7e00630bcae52c1da99831cf2f231
--- /dev/null
+++ b/hf_utils.py
@@ -0,0 +1,306 @@
+# Copyright 2024 MosaicML ComposeRL authors
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+from copy import deepcopy
+from dataclasses import dataclass
+from typing import (
+    Any,
+    Optional,
+    Union,
+)
+
+import numpy as np
+import torch
+import torch.nn as nn
+from transformers import (
+    AutoConfig,
+    AutoModelForCausalLM,
+    PretrainedConfig,
+    PreTrainedModel,
+)
+from transformers.modeling_outputs import ModelOutput
+
+
+@dataclass
+class SequenceClassifierOutput(ModelOutput):
+    """Sequence Classification Output.
+
+    Args:
+        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
+            Classification (or regression if config.num_labels==1) loss.
+        scores (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`):
+            Classification (or regression if config.num_labels==1) scores (before SoftMax).
+        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
+            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
+        past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
+            tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
+            `(batch_size, num_heads, sequence_length, embed_size_per_head)`)
+
+            Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
+            `past_key_values` input) to speed up sequential decoding.
+        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+            tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
+            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
+
+            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
+        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
+            tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
+            sequence_length)`.
+
+            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
+            heads.
+    """
+
+    loss: Optional[torch.FloatTensor] = None
+    scores: Optional[torch.FloatTensor] = None
+    logits: Optional[torch.FloatTensor] = None
+    past_key_values: Optional[tuple[tuple[torch.FloatTensor]]] = None
+    hidden_states: Optional[tuple[torch.FloatTensor, ...]] = None
+    attentions: Optional[tuple[torch.FloatTensor, ...]] = None
+
+
+class ValueHead(nn.Module):
+    """Value head for the transformer which outputs n_labels values."""
+
+    def __init__(self, n_labels: int, hidden_size: int, p_dropout: float = 0.0):
+        super().__init__()
+        self.dense = nn.Linear(hidden_size, hidden_size)
+        self.dropout = nn.Dropout(p_dropout)
+        self.score = nn.Linear(hidden_size, n_labels)
+        torch.nn.init.normal_(
+            self.score.weight,
+            std=1 / np.sqrt(hidden_size + 1),
+        )
+        torch.nn.init.constant_(self.score.bias, val=0.0)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        **kwargs: Any,
+    ) -> torch.Tensor:
+        hidden_states = self.dropout(hidden_states)
+        hidden_states = self.dense(hidden_states)
+        hidden_states = torch.tanh(hidden_states)
+        hidden_states = self.dropout(hidden_states)
+        output = self.score(hidden_states)
+        return output
+
+
+class RewardModelConfig(PretrainedConfig):
+    model_type = 'pairwise_rm'
+
+    def __init__(
+        self,
+        base_model: Optional[Union[str, os.PathLike]
+                            ] = 'meta-llama/Meta-Llama-3-70B-Instruct',
+        base_config: Optional[PretrainedConfig] = None,
+        p_dropout: float = 0.0,
+        n_labels: int = 1,
+        bias: float = 0.0,
+        return_logits: bool = False,
+        pretrain_cfg: Optional[dict[str, Any]] = None,
+        pretrained: bool = False,
+        **kwargs: Any,
+    ):
+        super().__init__(**kwargs)
+        self.base_model = base_model
+        self.base_config = base_config if base_config is not None else AutoConfig.from_pretrained(
+            base_model,
+        )
+        temp_config = deepcopy(self.base_config)
+        if not isinstance(temp_config, dict):
+            temp_config = temp_config.__dict__
+        for key, value in temp_config.items():
+            if key not in ['_name_or_path', 'architectures']:
+                setattr(self, key, value)
+        self.p_dropout = p_dropout
+        self.n_labels = n_labels
+        self.bias = bias
+        self.return_logits = return_logits
+        self.pretrain_cfg = pretrain_cfg if pretrain_cfg is not None else {}
+        self.pretrained = pretrained
+
+
+class AutoModelForCausalLMWithRM(PreTrainedModel):
+    config_class = RewardModelConfig
+    _supports_flash_attn_2 = True
+
+    def __init__(self, config: PretrainedConfig, *args: Any, **kwargs: Any):
+        super().__init__(config)
+        self.config = config
+        pretrain_cfg = config.pretrain_cfg
+        pretrained = config.pretrained
+        if pretrained:
+            self.lm_backbone = AutoModelForCausalLM.from_pretrained(
+                config.base_model,
+                config=config.base_config,
+                **pretrain_cfg,
+            )
+        else:
+            # When downloading from hub, base config gets converted to dict
+            # Redownload to make type PretrainedConfig
+            if isinstance(config.base_config, dict):
+                config.base_config = AutoConfig.from_pretrained(
+                    config.base_model,
+                    **config.base_config,
+                )
+            self.lm_backbone = AutoModelForCausalLM.from_config(
+                config.base_config,
+                **kwargs,
+            )
+        self.value_head = ValueHead(
+            n_labels=self.config.n_labels,
+            hidden_size=self.config.hidden_size,
+            p_dropout=self.config.p_dropout,
+        )
+
+    def generate(self, *args: Any, **kwargs: Any):
+        return self.lm_backbone.generate(**kwargs)
+
+    def resize_token_embeddings(
+        self,
+        new_num_tokens: Optional[int] = None,
+        pad_to_multiple_of: Optional[int] = None,
+    ) -> nn.Embedding:
+        # Note need to update vocab size in base config as well so lm_head modification happens
+        self.config.base_config.vocab_size = new_num_tokens
+        model_embeds = super().resize_token_embeddings(
+            new_num_tokens=new_num_tokens,
+            pad_to_multiple_of=pad_to_multiple_of,
+        )
+        return model_embeds
+
+    def set_input_embeddings(self, new_embeddings: Any):
+        return self.lm_backbone.set_input_embeddings(new_embeddings)
+
+    def get_input_embeddings(self):
+        return self.lm_backbone.get_input_embeddings()
+
+    def set_output_embeddings(self, new_embeddings: Any):
+        return self.lm_backbone.set_output_embeddings(new_embeddings)
+
+    def get_output_embeddings(self):
+        return self.lm_backbone.get_output_embeddings()
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Any] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **kwargs: Any,
+    ):
+        output = self.lm_backbone(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            labels=labels,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=True,
+            return_dict=True,
+            cache_position=cache_position,
+        )
+        scores = self.value_head(
+            output.hidden_states[-1],
+        ).squeeze(-1) - self.config.bias
+
+        logits = None
+        if self.config.return_logits:
+            logits = output.logits
+
+        return SequenceClassifierOutput(
+            loss=output.loss,
+            scores=scores,
+            logits=logits,
+            past_key_values=output.past_key_values,
+            hidden_states=output.hidden_states,
+            attentions=output.attentions,
+        )
+
+    @classmethod
+    def from_config(
+        cls,
+        config: PretrainedConfig,
+        **kwargs: Any,
+    ) -> PreTrainedModel:
+        config.pretrained = False
+        model = cls(config, **kwargs)
+        return model
+
+    @classmethod
+    def from_pretrained(
+        cls,
+        pretrained_model_name_or_path: Optional[Union[str, os.PathLike]],
+        *model_args: Any,
+        config: Optional[Union[PretrainedConfig, str, os.PathLike]] = None,
+        cache_dir: Optional[Union[str, os.PathLike]] = None,
+        ignore_mismatched_sizes: bool = False,
+        force_download: bool = False,
+        local_files_only: bool = False,
+        token: Optional[Union[str, bool]] = True,
+        revision: str = 'main',
+        use_safetensors: Optional[bool] = None,
+        **kwargs: Any,
+    ) -> PreTrainedModel:
+        trust_remote_code = kwargs.pop('trust_remote_code', None)
+        attn_implementation = kwargs.pop(
+            'attn_implementation',
+            'eager',
+        )
+        return_lm_logits = kwargs.pop('return_lm_logits', False)
+        load_in_8bit = kwargs.pop('load_in_8bit', False)
+
+        pretrained_model_config = AutoConfig.from_pretrained(
+            pretrained_model_name_or_path,
+            trust_remote_code=trust_remote_code,
+            token=token,
+            attn_implementation=attn_implementation,
+            use_cache=False,
+        )
+
+        if isinstance(pretrained_model_config, cls.config_class):
+            return super().from_pretrained(
+                pretrained_model_name_or_path,
+                *model_args,
+                config,
+                cache_dir,
+                ignore_mismatched_sizes,
+                force_download,
+                local_files_only,
+                token,
+                revision,
+                use_safetensors,
+                **kwargs,
+            )
+
+        pretrain_cfg = {
+            'trust_remote_code': trust_remote_code,
+            'token': token,
+            'load_in_8bit': load_in_8bit,
+            'attn_implementation': attn_implementation,
+        }
+
+        reward_model_config = RewardModelConfig(
+            base_model=pretrained_model_name_or_path,
+            base_config=pretrained_model_config,
+            hidden_size=pretrained_model_config.hidden_size,
+            return_logits=return_lm_logits,
+            vocab_size=pretrained_model_config.vocab_size,
+            pretrained=True,
+            pretrain_cfg=pretrain_cfg,
+        )
+
+        model = cls(reward_model_config)
+
+        return model
diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..686f7b13eb840c79203f503bbbb94ae5866d7383
--- /dev/null
+++ b/model-00001-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294f2c544bab1e1fcd24d396bf9b0b430548d6c3b13ae93d2df1ced7ac94f2e4
+size 4806705816
diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ff81dc8f2be0339019513118d608d81c0d0f9f99
--- /dev/null
+++ b/model-00002-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45267979b639d7e05cd34124d744c2f074f9223384812a2bc3bb77f7f052fa5
+size 4362142984
diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..486a89a0b263916ed34c48d957b19c9913eae372
--- /dev/null
+++ b/model-00003-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39d0e5e650b91d46492aa722f483f9e63889304f58d8a53a00aa124d5447e1c
+size 4362142984
diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4a0432a85af03d735712b92332b0e9fb856134ab
--- /dev/null
+++ b/model-00004-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e479a450802856cc3bd6d76c3e649d1013dbc529efef69dd66176c62f90d8424
+size 4966189056
diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5335b7ffbcb0f3081c97c98c7b0591cc42398a1a
--- /dev/null
+++ b/model-00005-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c05c6a13da37580bb30e84b556bf21beaa093fd1f8c7d0518e4ff35f09c5fd
+size 4362142984
diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..74f0f435e8b4e616e3cd9d6c443db138f4ca2c5f
--- /dev/null
+++ b/model-00006-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1d7caabb8b70ad7abce8b7d31b1923b156178c622f42be871fe55e1d306f17
+size 4362142984
diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8d02702750db683f391cb763995a5557d12dd7a5
--- /dev/null
+++ b/model-00007-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27893b8533d532911050b7e5c04cb731b43b98e0c1e8d057606dc740a6fdc43c
+size 4966189056
diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0f00ddef0d6bf3520759c6a4e48c0878f11dd1f5
--- /dev/null
+++ b/model-00008-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce21752cacbb59f10867a1f2cf69c53742066611ee687db1da34ad79e89a858
+size 4362142984
diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4a28f3da08d60dab1db2d654940c1cdded76ba04
--- /dev/null
+++ b/model-00009-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3acf3d4ac90a872fff3d2dbbda31c5d92ea1271e861e72e6d3d4b2d584ec1c
+size 4362143000
diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..146f7a99091cb3d995abd70d9ac64d9829cb447c
--- /dev/null
+++ b/model-00010-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240a7a49775b54ee334086758531882100a5cfdb87e71d84853e0cfecc54821a
+size 4966189072
diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f73c149833b09bf711eba55354916192ef759f8
--- /dev/null
+++ b/model-00011-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88dbb1975a09da766d69b3f1bc83b273bf5772a7e453d8e174c18e403b9ad79
+size 4362142992
diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6c20fd8cd004f514fdb0cc8f77ad2cabe630b371
--- /dev/null
+++ b/model-00012-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768055444d918661965c63dae18dfa4c09281980514f61b2d728502d4c5a0a54
+size 4362142992
diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..47425dcd3e5fed3c7fe2caeb400ff56023c1ee24
--- /dev/null
+++ b/model-00013-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2439d2dcb7305fc7838bf4014c703a50b9db1215af2deed5f1f7896bcf59e485
+size 4966189072
diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..749602512eb0e4ed1777cba09dc32b13ce34a860
--- /dev/null
+++ b/model-00014-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a874f6c22e630fb1eedc2f08b73d5c34919bf4c1ef291fdbafd8d0e45190a089
+size 4362142992
diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..297b5383429c50d8e4164b9c481950305bac404d
--- /dev/null
+++ b/model-00015-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e41f89d87ac154ad1223de04f62a84ba35ac9222316e5ead6524e349c7531e1
+size 4362142992
diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d56fb90cfcb43681f20c969431e1c756272d6265
--- /dev/null
+++ b/model-00016-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cad4f77a062fd926ce2af3241f34fbbddf5bbbfc4a491a1ae8a3e8fe32b7b11
+size 4966189072
diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7890b97670a25eed6a5335564433d239d3d8678c
--- /dev/null
+++ b/model-00017-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9021bb86b14cbc5daf81cfc51cdcd19ba81c09fcedc30bed2af6dc8199ef3c6
+size 4362142992
diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8cf5887ad20310b2c5651c03213d47f56d3d8dc3
--- /dev/null
+++ b/model-00018-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87b90390023a53ddfdcb97cbf0004c321d20fd7125d8a615120121ce234a0ea
+size 4362142992
diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..90d7fea6935143d662f2cc0b713309ef840a58d5
--- /dev/null
+++ b/model-00019-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27ba2f3df9a016f945c9665e24e32c86a96554f6e267b0e739f43e61dd7f8c3
+size 4966189072
diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a2392a4853dbe31ab4d8260841fb743cb01ae43c
--- /dev/null
+++ b/model-00020-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dc4585d95c6e1c12bfc1384d643c54bbad018311d7076261b844008d8c8853
+size 4362142992
diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..96a3946f0572134148fef176be56820f811fdb0e
--- /dev/null
+++ b/model-00021-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fa784ce853d334262bca9b3f37836baee8d68bb2783065e3d1c0164601a22a
+size 4362142992
diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ce46c1a73bc28980714985729e755333e9458fc7
--- /dev/null
+++ b/model-00022-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de3efe965be4687e15b6afb1a6c9da8471fd7bf171d49f9029ff5f1d7e661f4
+size 4966189072
diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f66ae40c6af5a38a13d485fb1c22cfbba5e362cf
--- /dev/null
+++ b/model-00023-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98eb9502d89332ff14eb8e65f5776764ba98d214c62e01bc9d5151bbcd9144d0
+size 4362142992
diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5f28da9761dbe83a8f107ec13e6792f864644b49
--- /dev/null
+++ b/model-00024-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39b517e68ca597f0ffb837a8cb0b19a1aa7aae340bcf107810b48a2e3192dba
+size 4362142992
diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bb05580db93e1707e7892546e91313c738b2ca52
--- /dev/null
+++ b/model-00025-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefd4d61e1ba813122e84a7f69a8199a3c015f5ac3bf24394fa5695b67536f20
+size 4966189072
diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..25bbb735b8e7832c5e85ad1ebaaced9ef5eac14a
--- /dev/null
+++ b/model-00026-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3498fb48422556940f9bbc365776c5163551a4cd1a45b8f869d5ccfb58ade5
+size 4362142992
diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ffcd82010f9c66b6051fc76c52c39e665e58c42d
--- /dev/null
+++ b/model-00027-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b879aedf4a02eeacc9c3ec23b0af54acb89caae79de3014aca21832e8ebaea3
+size 4362142992
diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7da0260d3032133ac707560a3df80d7a05e72f58
--- /dev/null
+++ b/model-00028-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cf5d18c822f7b405b83052713cdd02c4353d422f779132b5274eef8c4bc47c
+size 4966189072
diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..021f160c7bcb1bfacd5e441c56d9d53b2abc169c
--- /dev/null
+++ b/model-00029-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ec6869126f3f9ec5b013d9a715afdbcfd5b889d0b5bd41065e26670d00a432
+size 4362142992
diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f8b4ceb4d9905b0b179113e01997a3b50058beba
--- /dev/null
+++ b/model-00030-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814cac49bbbbaf5d4455e18410c3377a41d8e03f9049f58e891e01d7e8315a3a
+size 4362142992
diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a4945b1f9f14fb4f7478504184de364733eeb2bd
--- /dev/null
+++ b/model-00031-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dcb4ec8538da869260a4d09e6a4fb5a6e10f02680639afdc8fcbed3bc273e0
+size 4966189072
diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3817a70e68b728d605f7d92d82d507d069cf6c66
--- /dev/null
+++ b/model-00032-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b409bd1e6a074ddc81dbdb2fa842e9b951fb58c95cafdf862b3d65257ac96e0a
+size 4362142992
diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..efb6e259b10ab37f479925d27d75ebd7ff31bc95
--- /dev/null
+++ b/model-00033-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379bd098d8b979aafb003daf14058065e19e9812c2f2e77152cf1c601eea7392
+size 4362142992
diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e9dee1fac6596b4436fa820319434de62b752184
--- /dev/null
+++ b/model-00034-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f299b5588d46d160d7435963dc382666a1e9e3dbca5e3c8c5429c9ff1be614
+size 4966189072
diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5209e252e8ffb935cc50a5a3051353a7603ea3b8
--- /dev/null
+++ b/model-00035-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c636c1bf87959f616e34a3e4e582021fe62f91bc43803dc350830c02d18ecb4
+size 4362142992
diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1069434760f07a1997681511d9aff09172bf8635
--- /dev/null
+++ b/model-00036-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b39e569d4817387ffb4fe39bf3ba6a246d7cf11d5844e7b4f229b7b9dc21762
+size 4362142992
diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..027152d3652fa49c894846e92845f8bfc2b15611
--- /dev/null
+++ b/model-00037-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ad4a13b18b22aefcc82444271ebd69341e46ac099b8e03f5875eaede2f7dc2
+size 4966189072
diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..90d0814d13db535ead823ae0e63159e2baa0c4c8
--- /dev/null
+++ b/model-00038-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60984e9c2e9f6f1c40d8809b945183aacb958532d1a071f09d1c86a82969d1fa
+size 4362142992
diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..19b9f5f562677a9fe8a6d63c854cd3005c14383d
--- /dev/null
+++ b/model-00039-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a76ab605c7dfded0c9feb01d3f1bccb9de0e75105d4d0eb66bab36ab1b54af
+size 4362142992
diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..96f84642007ec2d5c2c9487179ad4de075dd19ea
--- /dev/null
+++ b/model-00040-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fce911e6e7d95c677e4c397a417db801df35d752e3f4794709e29ac2567fe5e
+size 4966189072
diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..68a5e1fa05ed7f9b53ee2418a8a07412ac9c5724
--- /dev/null
+++ b/model-00041-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55796d88008abb46d11cab60849080d4ea44b3733cef2be0c0bb3006ecf80558
+size 4362142992
diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ae38ba39261724469730a27077fa98c7b1ceba8f
--- /dev/null
+++ b/model-00042-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c246fe0c150de406ada31bece438a19070ce20ba9b3b8f55ba3df7ff1bb68305
+size 4362142992
diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..61c950f572aa3f4dba4576a54ddcb95904069336
--- /dev/null
+++ b/model-00043-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b00c7cb79bfa2a85c83bcf0743c5c2ec8eed8c9b13c9cab40d369eed3255d3
+size 4966189072
diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0d823f830a5abd1b9bf83d07825eb551fe5a5fcb
--- /dev/null
+++ b/model-00044-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa76b6f8caf68b36a98ba155bd961b53defc439aba68eb2e8ecc10df1eaf2b64
+size 4362142992
diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..64d46d1e8baab5447869a796e39e701758344209
--- /dev/null
+++ b/model-00045-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3ad35aeb5e6e23820516dc82827922f013f1941dc3dce7319a21ab6aa8c05b
+size 4362142992
diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f46e31d439e87ac04bb05c713c4dc3139e5a11c0
--- /dev/null
+++ b/model-00046-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550b9644a23e4293a325dc09828966d494a6652960bb133cc06b32bb90e31b83
+size 4966189072
diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e7fcbb1227c2032ffb380596df6951e7734e9b5
--- /dev/null
+++ b/model-00047-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78b3824b5cd04c0f4f447c75331698df27ba0fa370e3dc548211d416dc3bf81
+size 4362142992
diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..88c203b45382224fa9121f2d7dfe3f8552c6e08a
--- /dev/null
+++ b/model-00048-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8a591f4d1c71f19f1efe0db0c0077974aac2e077535251fd64309da154629f
+size 4362142992
diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f0bd2a6476286c3365217aaf272b5479436f04ff
--- /dev/null
+++ b/model-00049-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754cceb336651df239708f0ab79e7f65367f6bfa21e983b70ea9d2c54ef6c334
+size 4966189072
diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bfc5f6e6d596aabd2fd6cc65818185563279e692
--- /dev/null
+++ b/model-00050-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f94f580a33a023dd2815cb3d65b3be7e58d0cd727f7aab0d481e9e7863ed5e
+size 4362142992
diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..edf5ecd7697c7c623b33387230c2fba813e8b0ac
--- /dev/null
+++ b/model-00051-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342c2ff78cd7ca950117c37f9c14ea6d8d2733164acdad4b9bd7f92c8a0b681d
+size 4362142992
diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..486321b03a736200617e24f291c5dc9c19086ec5
--- /dev/null
+++ b/model-00052-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97951bdabf66361d265043d1a16c03487f7c665047903912e2f5721412a55372
+size 4966189072
diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca16c7ab349d3df2f261bb1764e5919a1b929f74
--- /dev/null
+++ b/model-00053-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c45b0cee46fe82b6420233215b1d79d0805182f66df24290c40a0c23000833b
+size 4362142992
diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..57234c7ac254186eae4312b02b4294652632d0f8
--- /dev/null
+++ b/model-00054-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0d28001dbed130d659653bdbc38d5859fa8c775cd74588c3d3abf1e16d7013
+size 4362142992
diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..94fb8a2425265694d2c4fe4571dabc462eb2be22
--- /dev/null
+++ b/model-00055-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b45e0655b804c2f5cfdc328ccaea875e2c162df4e25eddb3cd73ffcebf29862
+size 4966189072
diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b7b7f055f45faeadf75f010ee5ff68ae77a33ad0
--- /dev/null
+++ b/model-00056-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec8ce9edb31b0fc5b8d6eada569f66d04697eb181c1a4bda1b90045e1624209
+size 4362142992
diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8840e4c1a7986392a449d3b8c7f9832079590815
--- /dev/null
+++ b/model-00057-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493debbd041914b97d9ae1cffb187367c92dcc9d3e5efa0931ef2d9047160d6d
+size 4362142992
diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4a662fb0ae315eea790ba08f1377c2e63316bd82
--- /dev/null
+++ b/model-00058-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd38cfe8744dd829a245ef05d8d8f42f2c63a9ab3ff75638338903c42cfd277a
+size 4966189072
diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1c278e8e3772d397ca6fc31713c65fad71e4ff04
--- /dev/null
+++ b/model-00059-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1e405409628de76661e1e1dae2160593202cf91d84f86789bb9e5e936b21d8
+size 4362142992
diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7480d7cd4b1cc52e5b94c6283d40236b1a3150c3
--- /dev/null
+++ b/model-00060-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db02a925c342bce42e499ad31c38667d1046f3869b8e5efe157a6bd313878ec
+size 4362142992
diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ee7d96a53297a9781f5befcf3560f27a95522754
--- /dev/null
+++ b/model-00061-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fd921e0674e72ef7c496068c4cf7f6927467a80f3e9304097c4d806c3688be
+size 4362241656
diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40c4d42ff836d71af8515bf38164b70919af2a90
--- /dev/null
+++ b/model-00062-of-00062.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f77498cc84435aa762e14bb0c8cf387377058265460fcb11920d2ad792fc57f
+size 4471226900
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..f45a90a78d2c60f3e300f15f84474797ccc1d4d7
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,734 @@
+{
+  "metadata": {
+    "total_size": 282483392516
+  },
+  "weight_map": {
+    "lm_backbone.lm_head.weight": "model-00062-of-00062.safetensors",
+    "lm_backbone.model.embed_tokens.weight": "model-00001-of-00062.safetensors",
+    "lm_backbone.model.layers.0.input_layernorm.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.0.mlp.down_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.0.mlp.up_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00062.safetensors",
+    "lm_backbone.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00062.safetensors",
+    "lm_backbone.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00062.safetensors",
+    "lm_backbone.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00062.safetensors",
+    "lm_backbone.model.layers.1.input_layernorm.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.1.mlp.down_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.1.mlp.up_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.1.post_attention_layernorm.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00062.safetensors",
+    "lm_backbone.model.layers.10.input_layernorm.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.10.mlp.down_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.10.mlp.gate_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.10.mlp.up_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.10.post_attention_layernorm.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.10.self_attn.k_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.10.self_attn.o_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.10.self_attn.q_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.10.self_attn.v_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.11.input_layernorm.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.mlp.down_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.mlp.gate_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.mlp.up_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.post_attention_layernorm.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.self_attn.k_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.self_attn.o_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.self_attn.q_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.11.self_attn.v_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.12.input_layernorm.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.12.mlp.down_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.12.mlp.gate_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.12.mlp.up_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.12.post_attention_layernorm.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.12.self_attn.k_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.12.self_attn.o_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.12.self_attn.q_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.12.self_attn.v_proj.weight": "model-00010-of-00062.safetensors",
+    "lm_backbone.model.layers.13.input_layernorm.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.13.mlp.down_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.13.mlp.gate_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.13.mlp.up_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.13.post_attention_layernorm.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.13.self_attn.k_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.13.self_attn.o_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.13.self_attn.q_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.13.self_attn.v_proj.weight": "model-00011-of-00062.safetensors",
+    "lm_backbone.model.layers.14.input_layernorm.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.14.mlp.down_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.14.mlp.gate_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.14.mlp.up_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.14.post_attention_layernorm.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.14.self_attn.k_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.14.self_attn.o_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.14.self_attn.q_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.14.self_attn.v_proj.weight": "model-00012-of-00062.safetensors",
+    "lm_backbone.model.layers.15.input_layernorm.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.mlp.down_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.mlp.gate_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.mlp.up_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.post_attention_layernorm.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.self_attn.k_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.self_attn.o_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.self_attn.q_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.15.self_attn.v_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.16.input_layernorm.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.16.mlp.down_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.16.mlp.gate_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.16.mlp.up_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.16.post_attention_layernorm.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.16.self_attn.k_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.16.self_attn.o_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.16.self_attn.q_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.16.self_attn.v_proj.weight": "model-00013-of-00062.safetensors",
+    "lm_backbone.model.layers.17.input_layernorm.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.17.mlp.down_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.17.mlp.gate_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.17.mlp.up_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.17.post_attention_layernorm.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.17.self_attn.k_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.17.self_attn.o_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.17.self_attn.q_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.17.self_attn.v_proj.weight": "model-00014-of-00062.safetensors",
+    "lm_backbone.model.layers.18.input_layernorm.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.18.mlp.down_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.18.mlp.gate_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.18.mlp.up_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.18.post_attention_layernorm.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.18.self_attn.k_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.18.self_attn.o_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.18.self_attn.q_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.18.self_attn.v_proj.weight": "model-00015-of-00062.safetensors",
+    "lm_backbone.model.layers.19.input_layernorm.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.mlp.down_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.mlp.gate_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.mlp.up_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.post_attention_layernorm.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.self_attn.k_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.self_attn.o_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.self_attn.q_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.19.self_attn.v_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.2.input_layernorm.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.2.mlp.down_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.2.mlp.up_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.2.post_attention_layernorm.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00062.safetensors",
+    "lm_backbone.model.layers.20.input_layernorm.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.20.mlp.down_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.20.mlp.gate_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.20.mlp.up_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.20.post_attention_layernorm.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.20.self_attn.k_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.20.self_attn.o_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.20.self_attn.q_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.20.self_attn.v_proj.weight": "model-00016-of-00062.safetensors",
+    "lm_backbone.model.layers.21.input_layernorm.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.21.mlp.down_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.21.mlp.gate_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.21.mlp.up_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.21.post_attention_layernorm.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.21.self_attn.k_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.21.self_attn.o_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.21.self_attn.q_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.21.self_attn.v_proj.weight": "model-00017-of-00062.safetensors",
+    "lm_backbone.model.layers.22.input_layernorm.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.22.mlp.down_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.22.mlp.gate_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.22.mlp.up_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.22.post_attention_layernorm.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.22.self_attn.k_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.22.self_attn.o_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.22.self_attn.q_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.22.self_attn.v_proj.weight": "model-00018-of-00062.safetensors",
+    "lm_backbone.model.layers.23.input_layernorm.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.mlp.down_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.mlp.gate_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.mlp.up_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.post_attention_layernorm.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.self_attn.k_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.self_attn.o_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.self_attn.q_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.23.self_attn.v_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.24.input_layernorm.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.24.mlp.down_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.24.mlp.gate_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.24.mlp.up_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.24.post_attention_layernorm.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.24.self_attn.k_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.24.self_attn.o_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.24.self_attn.q_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.24.self_attn.v_proj.weight": "model-00019-of-00062.safetensors",
+    "lm_backbone.model.layers.25.input_layernorm.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.25.mlp.down_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.25.mlp.gate_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.25.mlp.up_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.25.post_attention_layernorm.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.25.self_attn.k_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.25.self_attn.o_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.25.self_attn.q_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.25.self_attn.v_proj.weight": "model-00020-of-00062.safetensors",
+    "lm_backbone.model.layers.26.input_layernorm.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.26.mlp.down_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.26.mlp.gate_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.26.mlp.up_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.26.post_attention_layernorm.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.26.self_attn.k_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.26.self_attn.o_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.26.self_attn.q_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.26.self_attn.v_proj.weight": "model-00021-of-00062.safetensors",
+    "lm_backbone.model.layers.27.input_layernorm.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.mlp.down_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.mlp.gate_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.mlp.up_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.post_attention_layernorm.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.self_attn.k_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.self_attn.o_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.self_attn.q_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.27.self_attn.v_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.28.input_layernorm.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.28.mlp.down_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.28.mlp.gate_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.28.mlp.up_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.28.post_attention_layernorm.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.28.self_attn.k_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.28.self_attn.o_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.28.self_attn.q_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.28.self_attn.v_proj.weight": "model-00022-of-00062.safetensors",
+    "lm_backbone.model.layers.29.input_layernorm.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.29.mlp.down_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.29.mlp.gate_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.29.mlp.up_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.29.post_attention_layernorm.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.29.self_attn.k_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.29.self_attn.o_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.29.self_attn.q_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.29.self_attn.v_proj.weight": "model-00023-of-00062.safetensors",
+    "lm_backbone.model.layers.3.input_layernorm.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.mlp.down_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.mlp.gate_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.mlp.up_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.post_attention_layernorm.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.self_attn.k_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.self_attn.o_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.30.input_layernorm.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.30.mlp.down_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.30.mlp.gate_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.30.mlp.up_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.30.post_attention_layernorm.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.30.self_attn.k_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.30.self_attn.o_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.30.self_attn.q_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.30.self_attn.v_proj.weight": "model-00024-of-00062.safetensors",
+    "lm_backbone.model.layers.31.input_layernorm.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.mlp.down_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.mlp.gate_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.mlp.up_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.post_attention_layernorm.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.self_attn.k_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.self_attn.o_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.self_attn.q_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.31.self_attn.v_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.32.input_layernorm.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.32.mlp.down_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.32.mlp.gate_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.32.mlp.up_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.32.post_attention_layernorm.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.32.self_attn.k_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.32.self_attn.o_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.32.self_attn.q_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.32.self_attn.v_proj.weight": "model-00025-of-00062.safetensors",
+    "lm_backbone.model.layers.33.input_layernorm.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.33.mlp.down_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.33.mlp.gate_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.33.mlp.up_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.33.post_attention_layernorm.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.33.self_attn.k_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.33.self_attn.o_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.33.self_attn.q_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.33.self_attn.v_proj.weight": "model-00026-of-00062.safetensors",
+    "lm_backbone.model.layers.34.input_layernorm.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.34.mlp.down_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.34.mlp.gate_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.34.mlp.up_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.34.post_attention_layernorm.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.34.self_attn.k_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.34.self_attn.o_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.34.self_attn.q_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.34.self_attn.v_proj.weight": "model-00027-of-00062.safetensors",
+    "lm_backbone.model.layers.35.input_layernorm.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.mlp.down_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.mlp.gate_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.mlp.up_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.post_attention_layernorm.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.self_attn.k_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.self_attn.o_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.self_attn.q_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.35.self_attn.v_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.36.input_layernorm.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.36.mlp.down_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.36.mlp.gate_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.36.mlp.up_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.36.post_attention_layernorm.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.36.self_attn.k_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.36.self_attn.o_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.36.self_attn.q_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.36.self_attn.v_proj.weight": "model-00028-of-00062.safetensors",
+    "lm_backbone.model.layers.37.input_layernorm.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.37.mlp.down_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.37.mlp.gate_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.37.mlp.up_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.37.post_attention_layernorm.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.37.self_attn.k_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.37.self_attn.o_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.37.self_attn.q_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.37.self_attn.v_proj.weight": "model-00029-of-00062.safetensors",
+    "lm_backbone.model.layers.38.input_layernorm.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.38.mlp.down_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.38.mlp.gate_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.38.mlp.up_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.38.post_attention_layernorm.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.38.self_attn.k_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.38.self_attn.o_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.38.self_attn.q_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.38.self_attn.v_proj.weight": "model-00030-of-00062.safetensors",
+    "lm_backbone.model.layers.39.input_layernorm.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.mlp.down_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.mlp.gate_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.mlp.up_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.post_attention_layernorm.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.self_attn.k_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.self_attn.o_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.self_attn.q_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.39.self_attn.v_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.4.input_layernorm.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.4.mlp.down_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.4.mlp.gate_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.4.mlp.up_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.4.post_attention_layernorm.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00062.safetensors",
+    "lm_backbone.model.layers.40.input_layernorm.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.40.mlp.down_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.40.mlp.gate_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.40.mlp.up_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.40.post_attention_layernorm.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.40.self_attn.k_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.40.self_attn.o_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.40.self_attn.q_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.40.self_attn.v_proj.weight": "model-00031-of-00062.safetensors",
+    "lm_backbone.model.layers.41.input_layernorm.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.41.mlp.down_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.41.mlp.gate_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.41.mlp.up_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.41.post_attention_layernorm.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.41.self_attn.k_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.41.self_attn.o_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.41.self_attn.q_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.41.self_attn.v_proj.weight": "model-00032-of-00062.safetensors",
+    "lm_backbone.model.layers.42.input_layernorm.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.42.mlp.down_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.42.mlp.gate_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.42.mlp.up_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.42.post_attention_layernorm.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.42.self_attn.k_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.42.self_attn.o_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.42.self_attn.q_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.42.self_attn.v_proj.weight": "model-00033-of-00062.safetensors",
+    "lm_backbone.model.layers.43.input_layernorm.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.mlp.down_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.mlp.gate_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.mlp.up_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.post_attention_layernorm.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.self_attn.k_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.self_attn.o_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.self_attn.q_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.43.self_attn.v_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.44.input_layernorm.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.44.mlp.down_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.44.mlp.gate_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.44.mlp.up_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.44.post_attention_layernorm.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.44.self_attn.k_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.44.self_attn.o_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.44.self_attn.q_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.44.self_attn.v_proj.weight": "model-00034-of-00062.safetensors",
+    "lm_backbone.model.layers.45.input_layernorm.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.45.mlp.down_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.45.mlp.gate_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.45.mlp.up_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.45.post_attention_layernorm.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.45.self_attn.k_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.45.self_attn.o_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.45.self_attn.q_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.45.self_attn.v_proj.weight": "model-00035-of-00062.safetensors",
+    "lm_backbone.model.layers.46.input_layernorm.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.46.mlp.down_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.46.mlp.gate_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.46.mlp.up_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.46.post_attention_layernorm.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.46.self_attn.k_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.46.self_attn.o_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.46.self_attn.q_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.46.self_attn.v_proj.weight": "model-00036-of-00062.safetensors",
+    "lm_backbone.model.layers.47.input_layernorm.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.mlp.down_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.mlp.gate_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.mlp.up_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.post_attention_layernorm.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.self_attn.k_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.self_attn.o_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.self_attn.q_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.47.self_attn.v_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.48.input_layernorm.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.48.mlp.down_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.48.mlp.gate_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.48.mlp.up_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.48.post_attention_layernorm.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.48.self_attn.k_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.48.self_attn.o_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.48.self_attn.q_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.48.self_attn.v_proj.weight": "model-00037-of-00062.safetensors",
+    "lm_backbone.model.layers.49.input_layernorm.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.49.mlp.down_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.49.mlp.gate_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.49.mlp.up_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.49.post_attention_layernorm.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.49.self_attn.k_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.49.self_attn.o_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.49.self_attn.q_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.49.self_attn.v_proj.weight": "model-00038-of-00062.safetensors",
+    "lm_backbone.model.layers.5.input_layernorm.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.5.mlp.down_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.5.mlp.gate_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.5.mlp.up_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.5.post_attention_layernorm.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.5.self_attn.k_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.5.self_attn.o_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.5.self_attn.q_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.5.self_attn.v_proj.weight": "model-00005-of-00062.safetensors",
+    "lm_backbone.model.layers.50.input_layernorm.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.50.mlp.down_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.50.mlp.gate_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.50.mlp.up_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.50.post_attention_layernorm.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.50.self_attn.k_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.50.self_attn.o_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.50.self_attn.q_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.50.self_attn.v_proj.weight": "model-00039-of-00062.safetensors",
+    "lm_backbone.model.layers.51.input_layernorm.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.mlp.down_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.mlp.gate_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.mlp.up_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.post_attention_layernorm.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.self_attn.k_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.self_attn.o_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.self_attn.q_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.51.self_attn.v_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.52.input_layernorm.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.52.mlp.down_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.52.mlp.gate_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.52.mlp.up_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.52.post_attention_layernorm.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.52.self_attn.k_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.52.self_attn.o_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.52.self_attn.q_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.52.self_attn.v_proj.weight": "model-00040-of-00062.safetensors",
+    "lm_backbone.model.layers.53.input_layernorm.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.53.mlp.down_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.53.mlp.gate_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.53.mlp.up_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.53.post_attention_layernorm.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.53.self_attn.k_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.53.self_attn.o_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.53.self_attn.q_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.53.self_attn.v_proj.weight": "model-00041-of-00062.safetensors",
+    "lm_backbone.model.layers.54.input_layernorm.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.54.mlp.down_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.54.mlp.gate_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.54.mlp.up_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.54.post_attention_layernorm.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.54.self_attn.k_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.54.self_attn.o_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.54.self_attn.q_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.54.self_attn.v_proj.weight": "model-00042-of-00062.safetensors",
+    "lm_backbone.model.layers.55.input_layernorm.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.mlp.down_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.mlp.gate_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.mlp.up_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.post_attention_layernorm.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.self_attn.k_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.self_attn.o_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.self_attn.q_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.55.self_attn.v_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.56.input_layernorm.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.56.mlp.down_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.56.mlp.gate_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.56.mlp.up_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.56.post_attention_layernorm.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.56.self_attn.k_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.56.self_attn.o_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.56.self_attn.q_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.56.self_attn.v_proj.weight": "model-00043-of-00062.safetensors",
+    "lm_backbone.model.layers.57.input_layernorm.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.57.mlp.down_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.57.mlp.gate_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.57.mlp.up_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.57.post_attention_layernorm.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.57.self_attn.k_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.57.self_attn.o_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.57.self_attn.q_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.57.self_attn.v_proj.weight": "model-00044-of-00062.safetensors",
+    "lm_backbone.model.layers.58.input_layernorm.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.58.mlp.down_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.58.mlp.gate_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.58.mlp.up_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.58.post_attention_layernorm.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.58.self_attn.k_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.58.self_attn.o_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.58.self_attn.q_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.58.self_attn.v_proj.weight": "model-00045-of-00062.safetensors",
+    "lm_backbone.model.layers.59.input_layernorm.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.mlp.down_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.mlp.gate_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.mlp.up_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.post_attention_layernorm.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.self_attn.k_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.self_attn.o_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.self_attn.q_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.59.self_attn.v_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.6.input_layernorm.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.6.mlp.down_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.6.mlp.gate_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.6.mlp.up_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.6.post_attention_layernorm.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.6.self_attn.k_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.6.self_attn.o_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.6.self_attn.q_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.6.self_attn.v_proj.weight": "model-00006-of-00062.safetensors",
+    "lm_backbone.model.layers.60.input_layernorm.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.60.mlp.down_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.60.mlp.gate_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.60.mlp.up_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.60.post_attention_layernorm.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.60.self_attn.k_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.60.self_attn.o_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.60.self_attn.q_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors",
+    "lm_backbone.model.layers.61.input_layernorm.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.61.mlp.down_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.61.mlp.gate_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.61.mlp.up_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.61.post_attention_layernorm.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.61.self_attn.k_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.61.self_attn.o_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.61.self_attn.q_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.61.self_attn.v_proj.weight": "model-00047-of-00062.safetensors",
+    "lm_backbone.model.layers.62.input_layernorm.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.62.mlp.down_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.62.mlp.gate_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.62.mlp.up_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.62.post_attention_layernorm.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.62.self_attn.k_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.62.self_attn.o_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.62.self_attn.q_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.62.self_attn.v_proj.weight": "model-00048-of-00062.safetensors",
+    "lm_backbone.model.layers.63.input_layernorm.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.mlp.down_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.mlp.gate_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.mlp.up_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.post_attention_layernorm.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.self_attn.k_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.self_attn.o_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.self_attn.q_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.63.self_attn.v_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.64.input_layernorm.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.64.mlp.down_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.64.mlp.gate_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.64.mlp.up_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.64.post_attention_layernorm.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.64.self_attn.k_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.64.self_attn.o_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.64.self_attn.q_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors",
+    "lm_backbone.model.layers.65.input_layernorm.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.65.mlp.down_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.65.mlp.gate_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.65.mlp.up_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.65.post_attention_layernorm.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.65.self_attn.k_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.65.self_attn.o_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.65.self_attn.q_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.65.self_attn.v_proj.weight": "model-00050-of-00062.safetensors",
+    "lm_backbone.model.layers.66.input_layernorm.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.66.mlp.down_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.66.mlp.gate_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.66.mlp.up_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.66.post_attention_layernorm.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.66.self_attn.k_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.66.self_attn.o_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.66.self_attn.q_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.66.self_attn.v_proj.weight": "model-00051-of-00062.safetensors",
+    "lm_backbone.model.layers.67.input_layernorm.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.mlp.down_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.mlp.gate_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.mlp.up_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.post_attention_layernorm.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.self_attn.k_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.self_attn.o_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.self_attn.q_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.67.self_attn.v_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.68.input_layernorm.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.68.mlp.down_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.68.mlp.gate_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.68.mlp.up_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.68.post_attention_layernorm.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.68.self_attn.k_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.68.self_attn.o_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.68.self_attn.q_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.68.self_attn.v_proj.weight": "model-00052-of-00062.safetensors",
+    "lm_backbone.model.layers.69.input_layernorm.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.69.mlp.down_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.69.mlp.gate_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.69.mlp.up_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.69.post_attention_layernorm.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.69.self_attn.k_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.69.self_attn.o_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.69.self_attn.q_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.69.self_attn.v_proj.weight": "model-00053-of-00062.safetensors",
+    "lm_backbone.model.layers.7.input_layernorm.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.mlp.down_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.mlp.gate_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.mlp.up_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.post_attention_layernorm.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.self_attn.k_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.self_attn.o_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.self_attn.q_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.7.self_attn.v_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.70.input_layernorm.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.70.mlp.down_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.70.mlp.gate_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.70.mlp.up_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.70.post_attention_layernorm.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.70.self_attn.k_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.70.self_attn.o_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.70.self_attn.q_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.70.self_attn.v_proj.weight": "model-00054-of-00062.safetensors",
+    "lm_backbone.model.layers.71.input_layernorm.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.mlp.down_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.mlp.up_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.post_attention_layernorm.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.self_attn.k_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.self_attn.o_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.self_attn.q_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.71.self_attn.v_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.72.input_layernorm.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.72.mlp.down_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.72.mlp.gate_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.72.mlp.up_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.72.post_attention_layernorm.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.72.self_attn.k_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.72.self_attn.o_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.72.self_attn.q_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.72.self_attn.v_proj.weight": "model-00055-of-00062.safetensors",
+    "lm_backbone.model.layers.73.input_layernorm.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.73.mlp.down_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.73.mlp.gate_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.73.mlp.up_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.73.post_attention_layernorm.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.73.self_attn.k_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.73.self_attn.o_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.73.self_attn.q_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.73.self_attn.v_proj.weight": "model-00056-of-00062.safetensors",
+    "lm_backbone.model.layers.74.input_layernorm.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.74.mlp.down_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.74.mlp.gate_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.74.mlp.up_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.74.post_attention_layernorm.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.74.self_attn.k_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.74.self_attn.o_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.74.self_attn.q_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.74.self_attn.v_proj.weight": "model-00057-of-00062.safetensors",
+    "lm_backbone.model.layers.75.input_layernorm.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.mlp.down_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.mlp.up_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.post_attention_layernorm.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.self_attn.k_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.self_attn.o_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.self_attn.q_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.76.input_layernorm.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.76.mlp.down_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.76.mlp.gate_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.76.mlp.up_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.76.post_attention_layernorm.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.76.self_attn.k_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.76.self_attn.o_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.76.self_attn.q_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.76.self_attn.v_proj.weight": "model-00058-of-00062.safetensors",
+    "lm_backbone.model.layers.77.input_layernorm.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.77.mlp.down_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.77.mlp.gate_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.77.mlp.up_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.77.post_attention_layernorm.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.77.self_attn.k_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.77.self_attn.o_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.77.self_attn.q_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.77.self_attn.v_proj.weight": "model-00059-of-00062.safetensors",
+    "lm_backbone.model.layers.78.input_layernorm.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.78.mlp.down_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.78.mlp.gate_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.78.mlp.up_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.78.post_attention_layernorm.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.78.self_attn.k_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.78.self_attn.o_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.78.self_attn.q_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.78.self_attn.v_proj.weight": "model-00060-of-00062.safetensors",
+    "lm_backbone.model.layers.79.input_layernorm.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.mlp.down_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.mlp.up_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.post_attention_layernorm.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.self_attn.k_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.self_attn.o_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.self_attn.q_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors",
+    "lm_backbone.model.layers.8.input_layernorm.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.8.mlp.down_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.8.mlp.gate_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.8.mlp.up_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.8.post_attention_layernorm.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.8.self_attn.k_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.8.self_attn.o_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.8.self_attn.q_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.8.self_attn.v_proj.weight": "model-00007-of-00062.safetensors",
+    "lm_backbone.model.layers.9.input_layernorm.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.9.mlp.down_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.9.mlp.gate_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.9.mlp.up_proj.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.9.post_attention_layernorm.weight": "model-00009-of-00062.safetensors",
+    "lm_backbone.model.layers.9.self_attn.k_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.9.self_attn.o_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.9.self_attn.q_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.layers.9.self_attn.v_proj.weight": "model-00008-of-00062.safetensors",
+    "lm_backbone.model.norm.weight": "model-00061-of-00062.safetensors",
+    "value_head.dense.bias": "model-00062-of-00062.safetensors",
+    "value_head.dense.weight": "model-00062-of-00062.safetensors",
+    "value_head.score.bias": "model-00062-of-00062.safetensors",
+    "value_head.score.weight": "model-00062-of-00062.safetensors"
+  }
+}