Upload HyperCLOVAX-SEED-Think-14B-rtn-mxfp4 model

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

chat_template.jinja

@@ -0,0 +1,100 @@
+{% if tools is not defined or tools is none %}
+    {{- '<|im_start|>tool_list\n<|im_end|>\n' }}
+{%- else %}
+    {{- '<|im_start|>tool_list\n[' }}
+    {%- for tool in tools %}
+        {{- '{"name": "' }}
+        {{- tool.function.name }}
+        {{- '", ' }}
+        {{- '"description": "' }}
+        {{- tool.function.description }}
+        {{- '"' }}
+        {%- if tool.function.parameters is defined %}
+            {{- ', "parameters": ' }}
+            {{- tool.function.parameters | tojson }}
+        {%- endif %}
+        {{- '}' }}
+        {%- if not loop.last %}
+            {{- ', ' }}
+        {%- endif %}
+    {%- endfor %}
+{{- ']<|im_end|>\n' }}
+{%- endif %}
+
+{%- set ns = namespace(is_searching=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.is_searching and (message.role == 'user' or message.role == 'tool') %}
+        {%- set ns.last_query_index = index %}
+        {%- set ns.is_searching = false %}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages %}
+    {%- if loop.index0 == 0 and message.role != 'system' %}
+        {{- '<|im_start|>system\n<|im_end|>\n' }}
+    {%- endif %}
+
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+
+    {%- set reasoning_content = '' %}
+    {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+        {%- set reasoning_content = message.reasoning_content %}    
+    {%- endif %}
+    {%- if message.role == "assistant" %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if reasoning_content %}
+                {{- '<|im_start|>assistant/think\n' + reasoning_content.strip('\n') + '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+
+        {%- if content %}
+            {{- '<|im_start|>assistant\n' + content.strip('\n') + '<|im_end|>' }}
+            {%- if message.tool_calls %}
+                {{- '\n' }}
+            {%- else %}
+                {{- '<|endofturn|>\n' }}
+            {%- endif %}
+        {%- endif %}
+
+        {%- if message.tool_calls %}
+            {{- '<|im_start|>assistant -> tool/function_call\n[' }}
+            {%- for tool_call in message.tool_calls %}
+                {%- if not loop.first %}
+                    {{- ', ' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}' }}
+                {%- endfor %}
+            {{- ']<|im_end|><|stop|>\n' }}
+
+        {%- endif %}
+    {%- elif message.role == "tool" %}
+        {{- '<|im_start|>tool/function_call\n' + content + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {%- if force_reasoning is defined and force_reasoning is true %}
+        {{- '<|im_start|>assistant/think\n' }}
+    {%- elif skip_reasoning is defined and skip_reasoning is true %}
+        {{- '<|im_start|>assistant\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "HyperCLOVAXForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig",
+    "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel",
+    "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM"
+  },
+  "bos_token_id": 100257,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "embedding_multiplier": 10.0,
+  "end_token_id": 100257,
+  "eos_token_id": 100257,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.012727922061357854,
+  "intermediate_size": 14336,
+  "logits_scaling": 0.125,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "hyperclovax",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 38,
+  "num_key_value_heads": 8,
+  "pad_token_id": 100257,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.embed_tokens"
+    ],
+    "quant_method": "mxfp4"
+  },
+  "resid_pdrop": 0.0,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 100000000,
+  "summary_first_dropout": 0.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_post_norm": true,
+  "vocab_size": 110592
+}

configuration_hyperclovax.py

@@ -0,0 +1,235 @@
+# coding=utf-8
+# This file was created for the HyperCLOVA X SEED 14B Think architecture.
+# partially copied and modified from https://github.com/huggingface/transformers
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""HyperCLOVAX model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+
+class HyperCLOVAXConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`HyperCLOVAXModel`]. It is used to instantiate an HyperCLOVAX
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the HyperCLOVAX.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 32000):
+            Vocabulary size of the HyperCLOVAX model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`HyperCLOVAXModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/main/perf_train_gpu_many#tensor-parallelism) to
+            understand more about it. This value is necessary to ensure exact reproducibility of the pretraining
+            results. Please refer to [this issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        attention_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        mlp_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in up_proj, down_proj and gate_proj layers in the MLP layers.
+        head_dim (`int`, *optional*):
+            The attention head dimension. If None, it will default to hidden_size // num_heads
+        embedding_multiplier (`float, *optional*, defaults to `None`):
+            Multiplier applied to the embedding weights. If `None`, it is equivalent to `1.0`.
+        logits_scaling (`float, *optional*, defaults to `None`):
+            Scaling factor for logits. If `None`, it is equivalent to `1.0`.
+        attention_multiplier (`float, *optional*, defaults to `None`):
+            Multiplier applied to the attention weights. If `None`, it is equivalent to `self.head_dim ** -0.5`.
+        residual_multiplier (`float, *optional*, defaults to `None`):
+            Scaling factor for residual connections. If `None`, it is equivalent to `1.0`.
+        use_post_norm (`bool`, *optional*, defaults to `False`):
+            Determines whether to apply Peri-Layer Normalization. Set to True to enable this feature.
+
+    ```python
+    >>> from transformers import HyperCLOVAXModel, HyperCLOVAXConfig
+
+    >>> # Initializing a HyperCLOVAX HyperCLOVAX style configuration
+    >>> configuration = HyperCLOVAXConfig()
+
+    >>> # Initializing a model from the HyperCLOVAX style configuration
+    >>> model = HyperCLOVAXModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "hyperclovax"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=32000,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        hidden_act="silu",
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        mlp_bias=False,
+        head_dim=None,
+        embedding_multiplier=None, # MuP
+        logits_scaling=None, # MuP
+        attention_multiplier=None, # MuP
+        residual_multiplier=None, # MuP
+        use_post_norm=False, # Peri-LN (post-norm)
+        auto_map={
+            "AutoConfig": "configuration_hyperclovax.HyperCLOVAXConfig",
+            "AutoModel": "modeling_hyperclovax.HyperCLOVAXModel",
+            "AutoModelForCausalLM": "modeling_hyperclovax.HyperCLOVAXForCausalLM"
+        },
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.mlp_bias = mlp_bias
+        self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, copy it it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        # rope_config_validation(self)
+
+        # MuP
+        self.embedding_multiplier = embedding_multiplier if embedding_multiplier is not None else 1.0
+        self.logits_scaling = logits_scaling if logits_scaling is not None else 1.0
+        self.attention_multiplier = attention_multiplier if attention_multiplier is not None else self.head_dim ** -0.5
+        self.residual_multiplier = residual_multiplier if residual_multiplier is not None else 1.0
+
+        # Peri-LN (post-norm)
+        self.use_post_norm = use_post_norm
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            auto_map=auto_map,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100257,
+  "transformers_version": "4.57.1",
+  "use_cache": false
+}

model-1-of-2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881b7cbf4e9d980e4004d651f67069d10f68ae2338c781af3499b4a6bac581a2
+size 5335802168

model-2-of-2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c02249dff8df983e6760647e97db198cf223db22c3870071d63540182897ca
+size 4496555288

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"model.layers.0.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.0.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.0.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.0.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.0.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.0.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.0.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.0.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.0.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.0.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.0.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.1.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.1.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.1.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.1.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.1.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.1.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.1.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.1.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.1.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.1.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.1.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.2.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.2.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.2.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.2.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.2.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.2.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.2.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.2.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.2.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.2.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.2.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.3.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.3.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.3.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.3.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.3.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.3.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.3.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.3.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.3.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.3.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.3.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.4.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.4.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.4.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.4.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.4.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.4.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.4.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.4.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.4.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.4.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.4.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.5.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.5.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.5.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.5.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.5.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.5.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.5.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.5.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.5.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.5.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.5.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.6.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.6.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.6.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.6.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.6.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.6.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.6.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.6.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.6.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.6.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.6.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.7.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.7.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.7.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.7.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.7.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.7.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.7.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.7.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.7.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.7.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.7.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.8.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.8.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.8.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.8.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.8.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.8.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.8.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.8.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.8.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.8.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.8.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.9.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.9.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.9.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.9.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.9.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.9.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.9.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.9.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.9.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.9.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.9.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.10.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.10.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.10.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.10.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.10.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.10.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.10.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.10.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.10.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.10.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.10.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.11.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.11.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.11.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.11.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.11.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.11.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.11.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.11.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.11.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.11.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.11.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.12.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.12.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.12.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.12.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.12.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.12.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.12.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.12.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.12.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.12.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.12.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.13.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.13.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.13.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.13.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.13.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.13.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.13.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.13.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.13.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.13.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.13.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.14.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.14.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.14.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.14.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.14.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.14.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.14.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.14.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.14.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.14.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.14.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.15.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.15.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.15.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.15.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.15.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.15.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.15.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.15.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.15.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.15.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.15.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.16.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.16.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.16.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.16.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.16.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.16.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.16.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.16.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.16.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.16.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.16.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.17.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.17.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.17.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.17.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.17.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.17.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.17.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.17.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.17.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.17.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.17.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.18.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.18.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.18.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.18.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.18.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.18.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.18.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.18.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.18.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.18.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.18.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.19.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.19.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.19.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.19.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.19.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.19.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.19.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.19.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.19.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.19.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.19.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.20.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.20.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.20.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.20.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.20.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.20.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.20.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.20.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.20.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.20.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.20.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.21.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.21.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.21.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.21.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.21.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.21.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.21.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.21.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.21.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.21.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.21.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.22.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.22.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.22.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.22.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.22.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.22.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.22.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.22.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.22.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.22.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.22.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.23.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.23.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.23.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.23.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.23.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.23.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.23.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.23.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.23.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.23.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.23.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.24.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.24.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.24.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.24.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.24.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.24.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.24.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.24.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.24.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.24.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.24.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.25.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.25.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.25.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.25.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.25.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.25.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.25.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.25.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.25.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.25.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.25.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.26.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.26.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.26.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.26.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.26.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.26.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.26.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.26.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.26.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.26.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.26.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.27.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.27.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.27.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.27.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.27.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.27.mlp.gate_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.mlp.gate_proj.scales": "model-1-of-2.safetensors", "model.layers.27.mlp.down_proj.blocks": "model-1-of-2.safetensors", "model.layers.27.mlp.down_proj.scales": "model-1-of-2.safetensors", "model.layers.27.input_layernorm.weight": "model-1-of-2.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-1-of-2.safetensors", "model.layers.27.post_norm1.weight": "model-1-of-2.safetensors", "model.layers.27.post_norm2.weight": "model-1-of-2.safetensors", "model.layers.28.self_attn.q_proj.blocks": "model-1-of-2.safetensors", "model.layers.28.self_attn.q_proj.scales": "model-1-of-2.safetensors", "model.layers.28.self_attn.k_proj.blocks": "model-1-of-2.safetensors", "model.layers.28.self_attn.k_proj.scales": "model-1-of-2.safetensors", "model.layers.28.self_attn.v_proj.blocks": "model-1-of-2.safetensors", "model.layers.28.self_attn.v_proj.scales": "model-1-of-2.safetensors", "model.layers.28.self_attn.o_proj.blocks": "model-1-of-2.safetensors", "model.layers.28.self_attn.o_proj.scales": "model-1-of-2.safetensors", "model.layers.28.mlp.up_proj.blocks": "model-1-of-2.safetensors", "model.layers.28.mlp.up_proj.scales": "model-1-of-2.safetensors", "model.layers.28.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.28.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.28.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.28.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.28.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.28.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.28.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.29.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.29.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.29.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.29.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.29.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.29.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.29.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.29.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.29.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.29.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.29.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.30.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.30.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.30.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.30.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.30.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.30.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.30.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.30.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.30.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.30.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.30.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.31.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.31.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.31.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.31.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.31.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.31.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.31.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.31.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.31.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.31.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.31.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.32.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.32.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.32.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.32.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.32.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.32.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.32.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.32.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.32.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.32.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.32.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.33.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.33.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.33.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.33.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.33.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.33.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.33.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.33.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.33.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.33.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.33.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.34.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.34.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.34.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.34.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.34.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.34.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.34.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.34.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.34.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.34.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.34.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.35.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.35.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.35.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.35.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.35.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.35.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.35.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.35.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.35.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.35.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.35.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.36.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.36.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.36.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.36.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.36.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.36.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.36.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.36.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.36.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.36.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.36.post_norm2.weight": "model-2-of-2.safetensors", "model.layers.37.self_attn.q_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.self_attn.q_proj.scales": "model-2-of-2.safetensors", "model.layers.37.self_attn.k_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.self_attn.k_proj.scales": "model-2-of-2.safetensors", "model.layers.37.self_attn.v_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.self_attn.v_proj.scales": "model-2-of-2.safetensors", "model.layers.37.self_attn.o_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.self_attn.o_proj.scales": "model-2-of-2.safetensors", "model.layers.37.mlp.up_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.mlp.up_proj.scales": "model-2-of-2.safetensors", "model.layers.37.mlp.gate_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.mlp.gate_proj.scales": "model-2-of-2.safetensors", "model.layers.37.mlp.down_proj.blocks": "model-2-of-2.safetensors", "model.layers.37.mlp.down_proj.scales": "model-2-of-2.safetensors", "model.layers.37.input_layernorm.weight": "model-2-of-2.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-2-of-2.safetensors", "model.layers.37.post_norm1.weight": "model-2-of-2.safetensors", "model.layers.37.post_norm2.weight": "model-2-of-2.safetensors", "model.embed_tokens.weight": "model-2-of-2.safetensors", "model.norm.weight": "model-2-of-2.safetensors", "lm_head.weight": "model-2-of-2.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}