create model

chat_template.jinja

@@ -0,0 +1,101 @@
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {%- set ns.system_prompt = ns.system_prompt + message['content'] %}
+            {%- set ns.is_first_sp = false %}
+        {%- else %}
+            {%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
+{%- if tools is defined and tools is not none %}
+    {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
+    {%- for tool in tools %}
+        {%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
+    {%- endfor %}
+    {%- if ns.system_prompt|length != 0 %}
+        {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
+    {%- else %}
+        {%- set ns.system_prompt = tool_ns.text %}
+    {%- endif %}
+{%- endif %}
+{{- bos_token }}
+{{- ns.system_prompt }}
+{%- set last_index = (messages|length - 1) %}
+{%- for message in messages %}
+    {%- set content = message['content'] %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_first = false -%}
+        {%- set ns.is_last_user = true -%}
+        {%- if loop.index0 == last_index %}
+            {{- '<｜User｜>' + content }}
+        {%- else %}
+            {{- '<｜User｜>' + content + '<｜Assistant｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {%- if '</think>' in content %}
+            {%- set content = (content.split('</think>')|last) %}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>'}}
+        {%- endif %}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_output_first = true %}
+        {%- for tool in message['tool_calls'] %}
+            {%- set arguments = tool['function']['arguments'] %}
+            {%- if arguments is not string %}
+                {%- set arguments = arguments|tojson %}
+            {%- endif %}
+            {%- if not ns.is_first %}
+                {%- if content is none %}
+                    {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                }
+                {%- else %}
+                    {{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                {%- endif %}
+                {%- set ns.is_first = true -%}
+            {%- else %}
+                {{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+            {%- endif %}
+        {%- endfor %}
+        {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
+            {%- set ns.is_tool = false -%}
+        {%- else %}
+            {{- content + '<｜end▁of▁sentence｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false -%}
+        {%- set ns.is_tool = true -%}
+        {%- if ns.is_output_first %}
+            {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+            {%- set ns.is_output_first = false %}
+        {%- else %}
+            {{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+{%- if ns.is_tool %}
+    {{- '<｜tool▁outputs▁end｜>'}}
+{%- endif %}
+{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
+{%- if add_generation_prompt and not ns.is_tool %}
+    {{- '<｜Assistant｜>'}}
+{%- endif %}

config.json

@@ -0,0 +1,118 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 2,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "model.layers.61.eh_proj",
+      "model.layers.61.shared_head.head",
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": 1,
+        "dtype": "fp8_e4m3",
+        "group_size": null,
+        "is_dynamic": true,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerChannelMinMaxObserver",
+        "qscheme": "per_channel",
+        "round_method": "half_even",
+        "scale_calculation_mode": null,
+        "scale_format": null,
+        "scale_type": "float",
+        "symmetric": true
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": 0,
+        "dtype": "fp8_e4m3",
+        "group_size": null,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerChannelMinMaxObserver",
+        "qscheme": "per_channel",
+        "round_method": "half_even",
+        "scale_calculation_mode": null,
+        "scale_format": null,
+        "scale_type": "float",
+        "symmetric": true
+      }
+    },
+    "kv_cache_post_rope": false,
+    "kv_cache_quant_config": {},
+    "layer_quant_config": {},
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null,
+    "version": "0.11+05471d7d04"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.57.1",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,199 @@
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    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 DeepSeek-V3.
+
+    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 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        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.
+        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. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *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.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        # 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.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        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,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a698e56b6c54393dcb6637c9b217b22140e999ecf5c58fb8050d7175d0aeaf38
+size 4996171024

model-00002-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798817233ff326fd1d029afefc1381592c5540c65e8929fd51eb219131159a6e
+size 4993855224

model-00003-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9e0036fc95c3f4f5a59e3f77ef86a6539d8efe6b0b14593885c2216af6b22c
+size 4993865912

model-00004-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b7a2df771d4756357ae5330c66143dd97eaddfdcba318f1b8255946a73514f
+size 4993860696

model-00005-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986e887927f6aaf5f8a999d523028955329448965996e032bc5e3e621484c47
+size 4993855672

model-00006-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1b721fd551fbf97567ff7b03d27962500dfe87a49562d973355bab8970cb70
+size 4993860648

model-00007-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c041802e30da2465a2be6c6ca21cb2304a5d2fc5d39181f609e295f8c6fb5d
+size 4993855496

model-00008-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41cce94a5380f722c071cf388be6cf62ad4d9a53c1e446ca6df7b90dcb4daddc
+size 4993860824

model-00009-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae029884dd4f1234a756fc808583730e0a7f35464b139e4c8e52cc735538c78
+size 4993865528

model-00010-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557c1f380105f6166c8cc44ee4de40cb21b107037e597d5481629a59f39bd245
+size 4993861080

model-00011-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ef28136dab8400dd7b67b6f58cdab7fa69107c5e0548cb96da3351cdb72fe6
+size 4993855032

model-00012-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00eeff1fb8dfdb6ff2e61c8009136ad97479f018629c0bb879d0c0b4c9bc62af
+size 4993855672

model-00013-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6f60be221491125d5a93dfbc4d4d13c21d2144342ced73c57e33c6f237042f
+size 4993860648

model-00014-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd4579efc61f33eb3148a9b2a4904a1e5b5c0854439e67c203827cf09d92613
+size 4993865792

model-00015-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb52fdc1f28401c2696d790f22e72ca126722fec3ad0674a67478e9ae20f3c08
+size 4993860768

model-00016-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44abc5c1f65b17e35df1a0879ce62ea9f4b767a2417b40d4bc6341b660c26338
+size 4993855344

model-00017-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63522254c845c7afd0254fad26c2efd0acb2275afa560fbef7d625d5c60fe1f
+size 4993861088

model-00018-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2efc3f967808af592e01f254609e4f40dac6d8910e512ee801f633be7f98c24
+size 4993855808

model-00019-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55345d1e656e6e6c1cc57ef7f86c581c298ee7096e4e2cb194cafbc59fbf16a
+size 4993866592

model-00020-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e78a1744aa43248f248f9ef5ce5ed5d80b33e28295548f7f44118fe9d5f5c9
+size 4993861320

model-00021-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79acb79697be84bdb3842ebe69f5942247343aa1c6a06c19417bad70ce772477
+size 4993856288

model-00022-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09116973655ce6478d6910e444f11c0522d5a4dcfbca90182af48d5ad9f98bae
+size 4993861376

model-00023-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7bf2459297354260b7d7c339cd912b76a6340d938e4b2e3f7db836c07fc036
+size 4993856080

model-00024-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba6126ccbdacc119d8222271ced033172024cebcef6af3c6da8359a8fe52476
+size 4993861584

model-00025-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cd59e9be859f37ad9e93f015bed8e110028710e32822824598e1f1479b98a8
+size 4993866112

model-00026-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ad2be32ad94fee963081f57fa7a76aaa7c4a634689c66d8d543cb42b0ba82c
+size 4993856352

model-00027-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f96cb296b5a127fdc65f9acc85a9abf09289a97913d9688b3ea3befcfcbe49a7
+size 4993861320

model-00028-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dbb0054575f9c5a45bd38f37c688d6cf60323178adb5b5f866e4f517d61362
+size 4993856344

model-00029-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e405c2c32bd12724ed422192356b60daf4a3b16e452223fd4e5f960aefc0035
+size 4993861320

model-00030-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc37b9ae599e80285d2f64758c243e1cdb01a1a9cfb01ec5fd09734a7f9e360a
+size 4993866376

model-00031-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b78412d81290733875ea104ccb07db12fb20228daba5f2c939a520ecef04f3
+size 4993861528

model-00032-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:547a970fd0940f6f1334ced3418f93fa3438c35f364437fd1d9935453239dc78
+size 4993855928

model-00033-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e96f7e5a8924f690f39bdcc1e5888bdeb6409daeacf38348393f0e5d776adab
+size 4997527104

model-00034-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca91cfe6e0c9eb97c47ddc900bb121b49237ba6f28fad4033224b1adb6e3737e
+size 4990190360

model-00035-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a559be95b623e39f7e23448c7b41bf95751a96a8899506e214f3c9c1a1591a
+size 4993866592

model-00036-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bfa5d9b81bf848d8cdc01ee77e46e0949d7b516df8c2a2f86aeb632ee622c5
+size 4993861320

model-00037-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64999974451a64df1765f40e687b8a5dbcfe39a8fffe33d0002bf9642edbe96a
+size 4993856192

model-00038-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee33814479be4499632d4e0e6f81e68205ec732e64260e9c9fa2c747a4d72135
+size 4993861472

model-00039-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bfd8032ec390a727f43cf2149ce8f267282eaa93c75b874ab67f7f890b31ed
+size 4993855984

model-00040-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0630768da9d68f63842677d9c59b10c89216b68d42c24c624d3a69d8e34c4d73
+size 4993861712

model-00041-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ab699a9cb2ca1c2b83efa24d4fc59f7a6d4094cb4d2ca7c5f6d2476ef40546
+size 4993865984

model-00042-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5ef68096df84044a8c3a67c630765aff525bde064420c35a0c1401b62b05a9
+size 4993856352

model-00043-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22da59a5235bff7eda0f42f20a9e0589e2b94936728ec0dd9cc05c83e0e7b971
+size 4993861320

model-00044-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62dc3523e619ffbd0b2bde10d1756a16337ac9fe12d7cde9dd5aabec19c121f3
+size 4993856248

model-00045-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25aee6e1da43902bff54eeeb8d6149e8648f4342790626d81d93162e8839ad5
+size 4993861416

model-00046-of-00138.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbf3abd6350673231094d314d63766ee0f9a5a386aea25f2f6a42d71dc82185
+size 4993866280