initial commit

README.md

@@ -1,3 +1,6 @@
 ---
 license: mit
 ---
+
+This is the  quantized version of the DeepSeek AI's DeepSeek V3 model,
+which quantized with [TensorRT Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer).

config.json

@@ -0,0 +1,70 @@
+{
+  "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": 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,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "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",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,210 @@
+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,
+        )

hf_quant_config.json

@@ -0,0 +1,258 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.25.0"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": null,
+        "group_size": 16,
+        "exclude_modules": [
+            "model.layers.23.self_attn*",
+            "model.layers.46.self_attn*",
+            "model.layers.25.post_attention_layernorm",
+            "model.layers.60.self_attn*",
+            "model.layers.47.mlp.gate",
+            "model.layers.42.input_layernorm",
+            "model.layers.43.self_attn*",
+            "model.layers.49.input_layernorm",
+            "model.layers.38.post_attention_layernorm",
+            "model.layers.53.mlp.gate",
+            "model.layers.40.self_attn*",
+            "model.layers.60.mlp.gate",
+            "model.layers.31.input_layernorm",
+            "model.layers.35.input_layernorm",
+            "model.layers.22.post_attention_layernorm",
+            "model.layers.27.input_layernorm",
+            "model.layers.53.input_layernorm",
+            "model.layers.2.post_attention_layernorm",
+            "model.layers.48.self_attn*",
+            "model.layers.8.self_attn*",
+            "model.layers.2.self_attn*",
+            "model.layers.43.input_layernorm",
+            "model.layers.30.self_attn*",
+            "model.layers.19.self_attn*",
+            "model.layers.31.mlp.gate",
+            "model.layers.10.self_attn*",
+            "model.layers.38.mlp.gate",
+            "model.layers.38.self_attn*",
+            "model.layers.14.mlp.gate",
+            "model.layers.42.mlp.gate",
+            "model.layers.1.self_attn*",
+            "model.layers.55.self_attn*",
+            "model.layers.37.input_layernorm",
+            "model.layers.32.post_attention_layernorm",
+            "model.layers.8.post_attention_layernorm",
+            "model.layers.36.self_attn*",
+            "model.layers.5.self_attn*",
+            "model.layers.4.self_attn*",
+            "model.layers.34.self_attn*",
+            "model.layers.59.post_attention_layernorm",
+            "model.layers.25.self_attn*",
+            "model.layers.22.input_layernorm",
+            "model.layers.21.self_attn*",
+            "model.layers.50.post_attention_layernorm",
+            "model.layers.7.mlp.gate",
+            "model.layers.25.mlp.gate",
+            "model.layers.32.input_layernorm",
+            "model.layers.51.self_attn*",
+            "model.layers.37.self_attn*",
+            "model.layers.20.self_attn*",
+            "model.layers.6.self_attn*",
+            "model.layers.60.input_layernorm",
+            "model.layers.46.input_layernorm",
+            "model.layers.44.self_attn*",
+            "model.layers.36.input_layernorm",
+            "model.layers.45.post_attention_layernorm",
+            "model.layers.55.post_attention_layernorm",
+            "model.layers.53.self_attn*",
+            "model.layers.13.input_layernorm",
+            "model.layers.33.input_layernorm",
+            "model.layers.58.self_attn*",
+            "model.layers.51.post_attention_layernorm",
+            "model.layers.30.mlp.gate",
+            "model.layers.18.self_attn*",
+            "model.layers.20.mlp.gate",
+            "model.layers.41.mlp.gate",
+            "model.layers.35.post_attention_layernorm",
+            "model.layers.9.post_attention_layernorm",
+            "model.layers.4.post_attention_layernorm",
+            "model.layers.28.post_attention_layernorm",
+            "model.layers.51.mlp.gate",
+            "model.layers.16.self_attn*",
+            "model.layers.5.mlp.gate",
+            "model.layers.44.post_attention_layernorm",
+            "model.layers.1.post_attention_layernorm",
+            "model.layers.36.mlp.gate",
+            "model.layers.35.self_attn*",
+            "model.layers.54.mlp.gate",
+            "model.layers.52.post_attention_layernorm",
+            "model.layers.22.mlp.gate",
+            "model.layers.15.mlp.gate",
+            "model.layers.32.self_attn*",
+            "model.layers.5.post_attention_layernorm",
+            "model.layers.23.input_layernorm",
+            "model.layers.9.self_attn*",
+            "model.layers.16.mlp.gate",
+            "model.layers.0.input_layernorm",
+            "model.layers.16.input_layernorm",
+            "model.layers.14.post_attention_layernorm",
+            "model.layers.39.input_layernorm",
+            "model.layers.27.post_attention_layernorm",
+            "model.layers.21.input_layernorm",
+            "model.layers.14.input_layernorm",
+            "model.layers.34.mlp.gate",
+            "model.layers.39.post_attention_layernorm",
+            "model.layers.21.mlp.gate",
+            "model.layers.7.post_attention_layernorm",
+            "model.layers.61*",
+            "model.layers.48.post_attention_layernorm",
+            "model.layers.17.self_attn*",
+            "model.layers.24.self_attn*",
+            "model.layers.12.mlp.gate",
+            "model.layers.11.post_attention_layernorm",
+            "model.layers.59.input_layernorm",
+            "model.layers.14.self_attn*",
+            "model.layers.26.input_layernorm",
+            "model.layers.50.mlp.gate",
+            "model.layers.45.self_attn*",
+            "model.layers.58.input_layernorm",
+            "model.layers.54.input_layernorm",
+            "model.layers.23.post_attention_layernorm",
+            "model.layers.59.self_attn*",
+            "model.layers.49.mlp.gate",
+            "model.layers.54.post_attention_layernorm",
+            "model.layers.45.mlp.gate",
+            "model.layers.2.input_layernorm",
+            "model.layers.7.self_attn*",
+            "model.layers.15.self_attn*",
+            "model.layers.49.self_attn*",
+            "model.layers.7.input_layernorm",
+            "model.layers.27.self_attn*",
+            "model.layers.26.post_attention_layernorm",
+            "model.layers.12.self_attn*",
+            "model.layers.8.mlp.gate",
+            "model.layers.35.mlp.gate",
+            "model.layers.38.input_layernorm",
+            "model.layers.55.mlp.gate",
+            "lm_head",
+            "model.layers.3.self_attn*",
+            "model.layers.32.mlp.gate",
+            "model.layers.22.self_attn*",
+            "model.layers.43.mlp.gate",
+            "model.layers.56.self_attn*",
+            "model.layers.18.mlp.gate",
+            "model.layers.57.input_layernorm",
+            "model.layers.47.self_attn*",
+            "model.layers.15.post_attention_layernorm",
+            "model.layers.0.self_attn*",
+            "model.layers.50.self_attn*",
+            "model.layers.33.post_attention_layernorm",
+            "model.layers.52.self_attn*",
+            "model.layers.42.self_attn*",
+            "model.layers.11.mlp.gate",
+            "model.layers.60.post_attention_layernorm",
+            "model.layers.49.post_attention_layernorm",
+            "model.layers.56.input_layernorm",
+            "model.layers.58.mlp.gate",
+            "model.layers.57.post_attention_layernorm",
+            "model.layers.9.input_layernorm",
+            "model.layers.37.post_attention_layernorm",
+            "model.layers.50.input_layernorm",
+            "model.layers.51.input_layernorm",
+            "model.norm",
+            "model.layers.12.post_attention_layernorm",
+            "model.layers.17.mlp.gate",
+            "model.layers.15.input_layernorm",
+            "model.layers.47.input_layernorm",
+            "model.layers.44.mlp.gate",
+            "model.layers.28.mlp.gate",
+            "model.layers.10.post_attention_layernorm",
+            "model.layers.11.self_attn*",
+            "model.layers.24.mlp.gate",
+            "model.layers.29.input_layernorm",
+            "model.layers.3.post_attention_layernorm",
+            "model.layers.19.post_attention_layernorm",
+            "model.layers.52.input_layernorm",
+            "model.layers.34.input_layernorm",
+            "model.layers.39.mlp.gate",
+            "model.layers.3.mlp.gate",
+            "model.layers.41.input_layernorm",
+            "model.layers.13.mlp.gate",
+            "model.layers.17.input_layernorm",
+            "model.layers.31.self_attn*",
+            "model.layers.59.mlp.gate",
+            "model.layers.46.mlp.gate",
+            "model.layers.29.self_attn*",
+            "model.layers.13.self_attn*",
+            "model.layers.17.post_attention_layernorm",
+            "model.layers.47.post_attention_layernorm",
+            "model.layers.4.mlp.gate",
+            "model.layers.56.mlp.gate",
+            "model.layers.54.self_attn*",
+            "model.layers.45.input_layernorm",
+            "model.layers.10.input_layernorm",
+            "model.layers.48.mlp.gate",
+            "model.layers.25.input_layernorm",
+            "model.layers.18.input_layernorm",
+            "model.layers.6.input_layernorm",
+            "model.layers.21.post_attention_layernorm",
+            "model.layers.34.post_attention_layernorm",
+            "model.layers.40.input_layernorm",
+            "model.layers.24.post_attention_layernorm",
+            "model.layers.28.input_layernorm",
+            "model.layers.1.input_layernorm",
+            "model.layers.12.input_layernorm",
+            "model.layers.0.post_attention_layernorm",
+            "model.layers.20.input_layernorm",
+            "model.layers.30.post_attention_layernorm",
+            "model.layers.57.mlp.gate",
+            "model.layers.13.post_attention_layernorm",
+            "model.layers.33.mlp.gate",
+            "model.layers.6.mlp.gate",
+            "model.layers.11.input_layernorm",
+            "model.layers.5.input_layernorm",
+            "model.layers.29.post_attention_layernorm",
+            "model.layers.28.self_attn*",
+            "model.layers.33.self_attn*",
+            "model.layers.29.mlp.gate",
+            "model.layers.26.mlp.gate",
+            "model.layers.27.mlp.gate",
+            "model.layers.8.input_layernorm",
+            "model.layers.40.mlp.gate",
+            "model.layers.42.post_attention_layernorm",
+            "model.layers.46.post_attention_layernorm",
+            "model.layers.48.input_layernorm",
+            "model.layers.10.mlp.gate",
+            "model.embed_tokens",
+            "model.layers.18.post_attention_layernorm",
+            "model.layers.40.post_attention_layernorm",
+            "model.layers.31.post_attention_layernorm",
+            "model.layers.57.self_attn*",
+            "model.layers.9.mlp.gate",
+            "model.layers.24.input_layernorm",
+            "model.layers.58.post_attention_layernorm",
+            "model.layers.6.post_attention_layernorm",
+            "model.layers.52.mlp.gate",
+            "model.layers.37.mlp.gate",
+            "model.layers.39.self_attn*",
+            "model.layers.56.post_attention_layernorm",
+            "model.layers.44.input_layernorm",
+            "model.layers.43.post_attention_layernorm",
+            "model.layers.16.post_attention_layernorm",
+            "model.layers.3.input_layernorm",
+            "model.layers.55.input_layernorm",
+            "model.layers.41.self_attn*",
+            "model.layers.20.post_attention_layernorm",
+            "model.layers.30.input_layernorm",
+            "model.layers.19.input_layernorm",
+            "model.layers.36.post_attention_layernorm",
+            "model.layers.41.post_attention_layernorm",
+            "model.layers.4.input_layernorm",
+            "model.layers.19.mlp.gate",
+            "model.layers.23.mlp.gate",
+            "model.layers.26.self_attn*",
+            "model.layers.53.post_attention_layernorm"
+        ]
+    }
+}

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f3a4495d6f25548a072c49f8e53a0e2cbdac9f6e88e55946284414109d08d3
+size 4832127568

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f747f3776f9a2a356e7805ec08cccb1824e4f41c576e0fa45854953b360724
+size 2419597576

model-00003-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c779b038f378b9794114a0444529cbeb2082910e474a2761a5aa14e9d804af
+size 2419598384

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8daf3a13e22605b93da4e56c048b165666414ac9d19ac58058814fd4835a20b
+size 2690159256

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd61fdd862d08bca177bd438dffae5758dc4d87c4b435d8f26181bc9bc475b2b
+size 2419597944

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e69092f2bb18bf8275efb0b0e283228a7b5009ca388487983a724dae9dd8234
+size 2727778936

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14f13b1fcf792e9b8364618e3679e290db9c1e14ed4a1cded807edc51e40caf
+size 2423268408

model-00008-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3994f0d50904124043c4b7628ab75c2fb3a8d8eb2189fbe37b6808b886c5e788
+size 2419598352

model-00009-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ec4a998e39a1999957008348543ab83ec5739dc3c62b9ee4f64f6924895d3b
+size 2690159640

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc12d5e87acdc7e5dbc3546ce635f8a168364ebe059409fcab915532374f8492
+size 2419597560

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76efe584b4cc519da179e7da79d93adf7eb6bcac86d3580ec92d3a69cfc6bd4c
+size 2419598384

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ecd4311f2b8e8cfe42012ef8837d7a3710b91243af727375a49e767903df28
+size 743249736

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ebbf09a672100bfb40c04b6efd9f784ce09adc16a08f6be00e6dc3e66984db
+size 2690130024

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d513aac6c2759ab6c40abe871c8aa65ffe78f4679fef5357c5e7ab572fb0a3e
+size 2419598296

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec610a4ddf05e86c0a9db7705160df9d9b1e0a56b4cd392ca5874fb1a28d3fa0
+size 2690159704

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272bd7a141800caf31d695d6a91903b8221f93e7cb651729dee07374fbf99abe
+size 2419597504

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8dee403517576cc12b7961e392688760d68f78c639a49d51dcc8babfd51cbd
+size 2419598384

model-00018-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fb1e4b7c736ac46a0dbd9346fadb7ceb00bfc29279579ddf63c5ccf359027c
+size 2690159320

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58226108ca46663288f15cbade6ca41cca5559cbf1622cf8bc8dc6b15a99d26e
+size 2419597880

model-00020-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6b0274045ac9b955c252267c745230d9d003ccf148167147c9fd64e82f050a
+size 2419598392

model-00021-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab46298d6d9616ef5a9eb512b96696232d14dde9e43292191c68bd44e9dd0ee5
+size 2690160048

model-00022-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b9f89c69b4e75d495fe7ca2a391d0ccfb4ced2dbe7ac69d6a662da57369c54
+size 2419599440

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04729179bfbdf34dfa5b87140656003ec073cf6ca68c43793cd8d6ab5d7640d
+size 2690160856

model-00024-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e99c5dc2006a603a55eb883a5d7855811f49814e6524344ed69eac6601a5e47
+size 2419598648

model-00025-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b3b11c6d03961b6123ee8dfc2e28e03cf197fd7929eae8872d570ac84c2622
+size 2419599560

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a05f71ece03a84ee02a44778fac6166b707b8dee2df1046182afa2b15973c3b
+size 2690160480

model-00027-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87e4ab3ef3936294d79afbb0ff580ac643128024d097f5d0273149a9d4aad6f
+size 2419599024

model-00028-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ef4561669f6ba1e9f94fbe86d15600471fa08296ecdb39b464d3c2d27a73f1
+size 2419599560

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e700338c37a6333f30775fae132d343353e0f00d930f8ae0fd9f535bfeb2fcce
+size 2690160104

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d727f15441b01d3e2c8fa9778adf1b3495e979fdbf8b5007b89b28dd465ae03
+size 2419599400

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5147602c2b4b94b38db9b799cea8d66632378bd92a7814f2032c789329b25807
+size 2690160896

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0ba1e0fb7a4f77c777feafa26a324246b51e48ad03719a4ba020cbf80fb9eb
+size 2419598608

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543a90dddf2fec3581fed668c231f404bf220fc1151a03ded5927a109d1656c5
+size 2419599568

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e59b2c6af8ce9cdc06242965b819f529d8fe28c936f58fd8ecd2649e24d4ab
+size 982732544

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8ca9492e50fc82104d7f1f7c579566f7c0f1e804c82b68ed1b3e4bdb211326
+size 2690131152

model-00036-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49755987ad6663a70c91f64620721f9604736f46f5c8a2b7451b6c6b922ec3b1
+size 2419599464

model-00037-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523f68a05fa7aa9dd446fc82aa9ec172d95a83015a5065ecdf166a4791cc845b
+size 2690160832

model-00038-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a98b02139228649e72a6e939710a68328d1a9e7a3a458489fe47e95727ea04e
+size 2419598672

model-00039-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71faa4ceda0867972300c72aaef09fb111102bad5a4cfe316eb683aca6d5963
+size 2419599560

model-00040-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e0904a985dbf7af19e3def7ae73f9f5e157c033d44db171253ab494cf035e0
+size 2690160448

model-00041-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6421dedc4cbbc1b08b1473d972729ac8f471a06130147d0684e220499a383c8b
+size 2419599056

model-00042-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3194dc4ead3b2e3e1d5bf90f066cbd3b2758b28a3deac8ee350dc0e9fe2d549
+size 2419599568

model-00043-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82f9c462859f78fe53ff1ffdff703464572c1594867a38721cfb5356e82bf8c
+size 2690160064

model-00044-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506546720d64b564419262d165f62bc22cf5eebe36d63f66d9e12a665cdf5000
+size 2419599440

model-00045-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fafeff81e5b7e6259a42f7522dd43e07288db0d4a8c19edd6fb348b8b4721c
+size 2690160856

model-00046-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81f35cbb2f1a0e2e9ddbec90adde8f77c2d95ca8c6331daeb504b64e43ba81b
+size 2419598648