Upload folder using huggingface_hub

chat_template.jinja

@@ -0,0 +1,3 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if not thinking is defined %}{% set thinking = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, 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 + '
+
+' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- if ns.is_last_user %}{{'<｜Assistant｜></think>'}}{%- endif %}{%- set ns.is_last_user = false -%}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- else %}{{message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'<｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜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) %}{%- if ns.is_last_user %}{{'<｜Assistant｜>'}}{%- if message['prefix'] is defined and message['prefix'] and thinking %}{{'<think>'}}  {%- else %}{{'</think>'}}{%- endif %}{%- endif %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{%- set content = message['content'] -%}{%- if '</think>' in content %}{%- set content = content.split('</think>', 1)[1] -%}{%- endif %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endfor -%}{%- if add_generation_prompt and ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{%- if not thinking %}{{'</think>'}}{%- else %}{{'<think>'}}{%- endif %}{% endif %}

config.json

@@ -0,0 +1,66 @@
+{
+    "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,
+    "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,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "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",
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.2",
+    "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,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1ae852f285ea5959d7a8417e1cc10ee9055d4fddda950553115a4bba1c9b7e
+size 3725148351

model-00002-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9cdbcbeffb16e7a617a07da50647513d4e9f33d6467b3626011006d9c2b832
+size 4361585928

model-00003-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43fe00bd0447ac90a2ca7508f49f80b09ed3c4bb50b79924070933f66100f9f2
+size 4227859220

model-00004-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1973d505986b80c07bede0c857885ca5bfbe886dfbea6db7dfb84e785c15d403
+size 4361585986

model-00005-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4adb1db71294ab83a6a39bed7d54aff97f3cc016c7b238a161658e1cad4f3ab6
+size 4361585948

model-00006-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50e89aeb9166cdf1aa7bc1e3b047e23ee29483962bf9505a8737ffbd411cd1c
+size 4227859220

model-00007-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89240aedcb8914dd5a48e82cb413824aedbd584dd2b9b174004aa8aa21b5f96
+size 4361585988

model-00008-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af427323475248f7cad02e3e224506b6b0492cfdd0d0d8e64925bc7358e1e454
+size 4361585934

model-00009-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89239587ebc7bcf2ed9e7102a507924be83b709d930a7fa79572dc3f5810aad9
+size 4227859220

model-00010-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e9597a2465e70ff395ae93eda208fdc9496b278970ef3df8e1b9c281cebc9c
+size 4361585986

model-00011-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf77be1a444e7993913dd8175a1e86f8d84a1d5d61b9e455e0e09aca27dc292
+size 4361585951

model-00012-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df05aa48d5ade1a4758203287ed5de2e77773da2acc86140e22301cc89104440
+size 4227859226

model-00013-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113ba6479c62744993a9e62734ae7b07077146a3b41f173333af0315c58329eb
+size 4361586014

model-00014-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea07b9cdcefda2c06a32906ce5825f8e2cf92dffc48beccad0765b451f56158f
+size 4361585984

model-00015-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01983ee6d2fa744da2eaee0ed392e9c6a0a5d94b5d6b3d630bcf90a05da18f9
+size 4227859226

model-00016-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfd8e0e18ab1aadd01384096355c93f1f26bb73dc6bcbaf5da3783faacdb8bc
+size 4361585988

model-00017-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb9838c96460846c43ae7215a836bad68abdc5aeb1ff9b505c155a84700d7a8
+size 4361585952

model-00018-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3b4bb45c8c18c67d181d34a0fe6128285e1718eb11256db5cfffcfbd8c5bdf
+size 4227859226

model-00019-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737e033442899a46e72abf2273ce5a1de1713198340b715103bd4739d03b29c2
+size 4361586016

model-00020-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19340315f183cc25920e4abddb3fe3b9cca700491e70b29fe93a8abeb4ce324c
+size 4361585972

model-00021-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48c1493951f62dc436bad86d51dd45e46153ad77c5a98e247498b84afc0002f
+size 4227859226

model-00022-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4756c81b64498c7e71d44409fc1e724767e8af5fbe6fa7304769887fd4927fb9
+size 4361586024

model-00023-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fa28713b67e55808b9e55b2349b900459d5f47be08ab37578f151aa73fcc47
+size 4361585948

model-00024-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc9f7e4b90fc0f043203226195bcb9272bef82cd5b6b408f36a54ad0832aaf4
+size 4227859228

model-00025-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224806e0e63ccf01b37194563dd840d4c24946bc81a5e7dea31b2b8a714bde4e
+size 4361586024

model-00026-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8571669da69e8b285d4d26d07166470442c9cbbc735f59e4387e3ae026e825fb
+size 4361585970

model-00027-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9ac53972afaa28174062806b91b926251af303da8f93a2ee9bcf061cf092ab
+size 4227859226

model-00028-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8aa4055ef0d7f62d0e80551c3c4dd136e55294f333e25936a913b55533d7b5
+size 4361586024

model-00029-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0075a519115e8d41f810b66bc6fe30387b8329751b139bc8f5bd45b53c5f83c
+size 4361585974

model-00030-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7843a3d8c35cba887ef8f683b8815f164e4ee53485378c9ec50d5372989cd262
+size 4227859226

model-00031-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b87453e813fe224b8a33a4219cf54edec593e6c6a9a267a224867272177b392
+size 4361586022

model-00032-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f03cab42d022c11e79430bac9a4aff9ff8b3088206348d02042ee9267b33cad
+size 4361585972

model-00033-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6441867f322f4cf344de5320d85d0938ad4ff2f379d82b5ee4033b313916938e
+size 4227859228

model-00034-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63bde1b183898e1d20abb7af4ae17b68d188628688817103b40b8b24437cc7e
+size 4361586026

model-00035-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958c3c3d8e7940b9172a755d07ba322e2fb7e786e5d065d745dadb8d56dee1aa
+size 4361585956

model-00036-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63925d27c0ada11f8fde287d1dea2870366b3c97c1481ecba4484c2b16548bd1
+size 4227859226

model-00037-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be818800c768959ce2c88df1ec74738ce4e9d278e0228cc30af45c94c96c3969
+size 4361586026

model-00038-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0079f7fd29743f5bad02f1ed9270510c938ca50d1d3709cee60edb62203b7584
+size 4361585978

model-00039-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d148324c443fe1aa281417e5ad48b79a88895fb3c3d789cc77963c6c56c8b8f5
+size 4227859222

model-00040-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa293a507110e22cc4b84675728809d158c3b12ce9a38320bc08381f1f31eac
+size 4361586024

model-00041-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee295b09edb0d10cfcbe0699dc82f4dc56a268bb417815c8146d3eaa6c28921
+size 4361585974

model-00042-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65251007f124a10bac0d86b84dc46e4322024ee63f4b90251bf7118408b39cfe
+size 4227859228

model-00043-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36eb544b03efbbd1c7245552a687f2888d6fc8d3f34935fd89bfc03635efd571
+size 4361586022

model-00044-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afb041b2d15bd715a1a76e3a315981028d28880353c265f158d9ea22d2ac103
+size 4361585988

model-00045-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82aa62cca6956a264fb22c7c52c380ad255678d8e8b6fc17198756efa5c0906d
+size 4227859228

model-00046-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2b2fd9c79bf92969df90076178b016d645ff29047582f2e22fbd75261525e0
+size 4361586012