Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,37 @@
+{% if tools -%}
+    {{ '<|im_system|>tool_declare<|im_middle|>' -}}
+    {{- tools | tojson -}}
+    {{ '<|im_end|>' -}}
+{%- endif -%}
+
+{%- for message in messages -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+    {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}
+  {%- endif -%}
+  {%- if message['role'] == 'system' -%}
+    {{ '<|im_system|>system<|im_middle|>' }}
+  {%- elif message['role'] == 'user' -%}
+    {{ '<|im_user|>user<|im_middle|>' }}
+  {%- elif message['role'] == 'assistant' -%}
+    {{ '<|im_assistant|>assistant<|im_middle|>' }}
+  {%- elif message['role'] == 'tool' -%}
+    {{ '<|im_system|>tool<|im_middle|>' }}
+  {%- endif -%}
+
+  {%- if message['content'] is string -%}
+    {{- message['content'] + '<|im_end|>' -}}
+  {%- else -%}
+    {%- for content in message['content'] -%}
+      {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+        {{ '<|media_start|>image<|media_content|><|media_pad|><|media_end|>' }}
+      {%- else -%}
+        {{ content['text'] }}
+      {%- endif -%}
+    {%- endfor -%}
+    {{ '<|im_end|>' }}
+  {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+  {{ '<|im_assistant|>assistant<|im_middle|>' }}
+{%- endif -%}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 163584,
+  "eos_token_id": 163585,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 131072,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 384,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 0,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 64,
+    "modules_to_not_convert": [
+      ".mlp.gate$"
+    ],
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 1.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 50000.0,
+  "routed_scaling_factor": 2.827,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": false,
+  "v_head_dim": 128,
+  "vocab_size": 163840
+}

configuration_deepseek.py

@@ -0,0 +1,212 @@
+# Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+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.
+        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/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. 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',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        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,
+        pretraining_tp=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
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # 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
+
+        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 +1,6 @@
+{
+  "do_sample": true,
+  "eos_token_id": 163585,
+  "max_length": 131072,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256c3a67fa4654c3a7f4f13dd0eca482c7f7d91d2362896d7e9c0a49c12dc3f8
+size 4998206416

model-00002-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816ae757d8a2604005c06f62363e95d8f8a5297d1f3febe9490dd035e406548b
+size 4993633312

model-00003-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f8ddf69610b83c704a978324f3aa7dce672d99c1db4a3e3b2bdbc56614fd1b
+size 4998287608

model-00004-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7826ddeda5d7c255f8ccc798a438f339792e26e9aee395eb4396bc4ff4e3c5d
+size 4993633320

model-00005-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b8c25a4c7dbb92ef665974e4fe5663aa8c81aa332870c9e63fcc55b3c17cd3
+size 4998287608

model-00006-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9abfcd29e530b1ba91d36145cf520a6f17f76fc9c2cb5f8b0d92e5ce8e56ba8
+size 4993633328

model-00007-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34f1101d669293afc28b1826c13b3dde04b0ad39b61e009b603d0c25c1f3b48
+size 4998287608

model-00008-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e75bb5b595ec48c0979a437e6de2af54bb390d8bf072f64076e0f501061dbf
+size 4998288320

model-00009-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f082449cb0741af24b67d36f162ff82312c9219590fb444293e7ffd3fd3c00
+size 4993632616

model-00010-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb728e66174c8937324fff5ded4c3093a9ff691b0a03809d58a134bfd268e4ea
+size 4998288024

model-00011-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1161aa6c61b92beadcd1ab4fe80af58fb1a8290a2f717c0142367349ed60611
+size 4993632912

model-00012-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db3568a45c8677fea02c3a5d9b5c8cb2e8a4748d04af57bb53545eb8413696f
+size 4998287720

model-00013-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedb70528214886402ac0fcf390929c622927174e9fb9cdc706a7591fb9c1400
+size 4993633216

model-00014-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83f91aa2957369b7fe57580ccde245d691fefc383bc96b012fef58d308bcd20
+size 4998287608

model-00015-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd409189cc0575c57aa5f9f15a88380708456b559b6473a0835dce32362b650
+size 4993633328

model-00016-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e10c46380962d01d1ec7a47b3a0c766b35e82d2e9e2ca7f4c2f6d57bf855d33
+size 4998287608

model-00017-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03a8dc930811f061830c0a0d4129e69b819f263f64d79da034971e382c1f385
+size 4993633320

model-00018-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6904f6912c4a096a0754c6b7b34bb1127758de32bf2f8147e6f0ecf077ce5a91
+size 4998289320

model-00019-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d35d5a74174b80e450d72b1e8feff5661589254e433e64fc5ae78da68b1c0ab
+size 4998290304

model-00020-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f62fc2b83c7fe35905bac742c0112b80daaae24cac01c6b3faa6330a5504347
+size 4993634416

model-00021-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8542f577f687949e971408ca465ab0285c09b9af8e5f944ab2f7e83a98fb95
+size 4998290008

model-00022-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e34e40af8bf55f8dfea065fb480697fbf845ff589a9f7b49d96a66979545fe5
+size 4993634712

model-00023-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1dcbb51ab7dfbdb0bef4b4b870ff6dfd48dcf9248fcf079d187c9a61906632
+size 4998289704

model-00024-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ca7d97f8c16b1c7619c354cd818c43a383449786d62d965325caafef3f5627
+size 4993635008

model-00025-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972eab6d19c18235821272c8e9a8313388c1c5a04a3cdd8c9a1bdd6499f2ce62
+size 4998289504

model-00026-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80185c32c726a3eeb2c361903701215e36b7c1024a7d5469b233ca43b1258e1
+size 4993635216

model-00027-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce8a4d9ec9af8eef676933ad5852eaaae68b39d3766162c1bb931cb6a72d3f6
+size 4998289504

model-00028-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327067456c5f11f33946d15c3bbff1b7404e6ea6ff0f7b9d957d648e89df0bb1
+size 4993635216

model-00029-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16cdcc83c51ce9016f274a48dab21895c0e4684ba8d1fc3b8956cf3150910439
+size 4998289504

model-00030-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b903597f8c2c311fa7d758eef86e34cf8b53eb8299485a880ad17419b81263c
+size 4998290488

model-00031-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514e1f3d356062ac94c8acd7076dcffa1a94eeeb44c88f1cc4a191e4e397c5a8
+size 4993634232

model-00032-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076aacbd111b06a6857e2e66beb2391b38e7c5d6b05be8f265be9f076aefc1ff
+size 4998290104

model-00033-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6f8313439d23dbeeafcc2b8b7f7e96bdb44c944fbddcad3d811510faddc9ac
+size 4993634624

model-00034-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776ed3f9e0c26aaae28d0406e981edfc243b225bbd0cbd3297ea6db9635baa57
+size 4998289800

model-00035-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c17e1cbf614902d0725c453a9391e46045ab205f610d65dcb8dad110d1da09
+size 4993634920

model-00036-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23782a852a6e55125eca44318ab19b792ff9b67e561665be549c9522d1c6824a
+size 4998289504

model-00037-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f50ac007c0382b504bfdb4338042a2946219cb9690a1395c6e5ddd582471e1b
+size 4993635216

model-00038-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35487497835e7db3435e64346f9f40c0e651498e542815957e7ecf986f92bc7c
+size 4998289504

model-00039-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6201b4be03c4b6d7cde202c832f216f3635073bd09910bac5a609fb24c191aa3
+size 4993635216

model-00040-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5634802faeddae1321e5a9f6bbb62460c4641577149a5837455ae177b5c089aa
+size 4998289504

model-00041-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14112e52bed29525d1dbe8aa2856ca605a4d947964ca35e49c9740318abf230e
+size 4993635216

model-00042-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56e7843d1fd161cbd2d99c335ae987c2e130957b8f23de9718d3230722d5caa
+size 4998289504

model-00043-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a66bc829081cf83d7d59c57936d8f22bad2ca5ec535a02711eb5486589bde01
+size 4998290192

model-00044-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e98881118bdd0e58d39ae836950977a36b623c8e27e5b6223b0a8db6e121ff9
+size 4993634520

model-00045-of-00112.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53185fc0c184dd605c873fbe259a4ab5cbf21b780684f1bfe2c441ac70a22c2
+size 4998289896