initial commit

README.md

@@ -1,3 +1,5 @@
 ---
 license: mit
 ---
+This is the  quantized version of the DeepSeek AI's DeepSeek-V3-0324 model,
+which quantized with [TensorRT Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer).

config.json

@@ -0,0 +1,67 @@
+{
+  "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_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",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "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,
+        )

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

model-00001-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cadc7fdf96bc3dc12e6bd9617da98f30779ee30e698a84099a1a7951e6ca40
+size 4832127568

model-00002-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0c3eed9d63b475b54f8820f3fdefb987a557f10251c03e1ad747fc477f7aa7
+size 2419597576

model-00003-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080b18edf3202fd2b0714119e2305b7e451c6f2b6b77788bd46222f286bb895e
+size 2419598384

model-00004-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0a26fa5069a36a71bf4d6c13deba38d4e519a3f139aeb5b27e95d8fa87eedb
+size 2690159256

model-00005-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8e9084bd935c2765d05cf413de9aef063252508a43006a9397e47b984e2015
+size 2419597944

model-00006-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbd421b7690e11b769c5a6892bf7dfd99cd458b2feb8e597d320decad95f9c5
+size 2727778936

model-00007-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d32f362b3fadfa1ca2a22a0cd39491f550a57f4e8ce54a650e861f78d8d0adc
+size 2423268408

model-00008-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fafa97ba0b92acb18d785f166bd704f44eb0eaac1a4fe6dab73df329bc1c7f8
+size 2419598352

model-00009-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afda88ef7cc13d7fb5afe9290c8c9a2e5b86eacdb837194ab9b52be7e245a94
+size 2690159640

model-00010-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fcfa476354915d107213110e177e23d6d52aadd32e9913c4a53a0d96df4706
+size 2419597560

model-00011-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba8fec5e0a4129618409d32b8a4c80c12751b2bb3497bd2c31316046c251cd7
+size 2419598384

model-00012-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d86b55fd5491fadf90f74ba9e13f0e6aaf4d8be09d390752efbeaa15b552352
+size 743249736

model-00013-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb981ba0ac27975a2ee7e40465f91990bae49dd5b63393a7246b2c50bd91f7d3
+size 2690130024

model-00014-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c21bd53418233d8731e00f4fb97c21c1b4abeb2339f94c7c73cf43263549f49
+size 2419598296

model-00015-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d147381a4fbd367a440e4b27868d710a27d70cfe1021c58cc1747ffebe3ec3cb
+size 2690159704

model-00016-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6799744744d553e1222b0e32526ba30f752f7d711631616b99514c708a5562e4
+size 2419597504

model-00017-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6aa2206f8842e74790c7d919da1fdb6220e281d5a8c44595ec0b130c0caee8
+size 2419598384

model-00018-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d519b8448bce87fef3f2caa742225e6d8a097540de563d2200345de7cb49978a
+size 2690159320

model-00019-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce35ee175af569415a662e2c349f542d13c12729cd457f46d0b30abd23c7f7c1
+size 2419597880

model-00020-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee65e7b0fdfc27047b9f9558f9a631640db392df7312b94be582ff39c6971e2
+size 2419598392

model-00021-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e676ef9aae18b4aae7d2a14a8d96cedf8a0976d0ff4405cd49ce18f23292cbd3
+size 2690160048

model-00022-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dc3077f85889ea58046181b2a172a959532e8b551fe7f033d5bf5fe470e709
+size 2419599440

model-00023-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b396b82845659d95b693ba49199b39a3321b56977cf31b35ca8c96b000d0bb29
+size 2690160856

model-00024-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ef2ab7427166eb5f4f56a5bf983fa94db02db317fa6c60d393f7c445855c96
+size 2419598648

model-00025-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897de1dcfa742a487d11d961126d8b0725f1a7a2c6afb4ef3cb71e55538d839e
+size 2419599560

model-00026-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a59b38627317e4a7d108bf5c8d3b5a51ba9cbcee590063a0152a48187028a9
+size 2690160480

model-00027-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64510306eb5181c9620d7d25d24b852b47defb9c072b2128398b03e32f1c8a6
+size 2419599024

model-00028-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a08a556e72cd854aa8f769d39aa6de83bb9fcc4aaff6425f9055387a81c27a
+size 2419599560

model-00029-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7838807b09df865fa1a4d6eca3f949880cfa766b24aad46a20c79b1a617d09b6
+size 2690160104

model-00030-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdfce0219652d797bd39d83cda365395e5dc05f46a8e2234c8b3591b24b53c5
+size 2419599400

model-00031-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3c94b920e3799284fd39a73f0e4a7dfcf0c302b90983a0aaa3b68aba6d61fe
+size 2690160896

model-00032-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113ca734e35f42da580230d015792780954d8414c6d0e4eee46e78896976168e
+size 2419598608

model-00033-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d70dc2977abe1caa73da7a618396b5909e1aaa9a50bb5ee732005392ce105c
+size 2419599568

model-00034-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afdde383a7d5c11922beb1039dc5115e7825a9e53047cc44a6a6df8d84fe5b73
+size 982732544

model-00035-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a882671343008ea600c501b6d00c49830b8d4e78151ea09071d1e360916a8b18
+size 2690131152

model-00036-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d46607961a8aa78106ee135911b499583544eedb3d49dd4d94ca59817f60fa0
+size 2419599464

model-00037-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b74d87c747dcda43dbf24748bd0ee9ca97845e3e45c143912d385f45152b41
+size 2690160832

model-00038-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaa775c460c990cd2ba313ce9ce77b70a2ca4f2a0b2629385fb8a547e0924bd
+size 2419598672

model-00039-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75be450bff6bbea756b605f0e3b832bca14d2f9df95e737581aab949cd274633
+size 2419599560

model-00040-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ab8702be2162198a892ae5e4b88092e4587b528f99c1a757ea24df4ee8830d
+size 2690160448

model-00041-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b133c6eeb4f9c4c0918e604c791a3536a4d1b90df603c7ad03fc9a87772c0a
+size 2419599056

model-00042-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c332015157d0660341d067f456d74c43520a1c09ef40452e31879eda3c394a9
+size 2419599568

model-00043-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54e2f2135e01f717473435cc4a651c5fe347cce399d77f0c4ba21ff57a3a41f
+size 2690160064

model-00044-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ec9bb478e73f3369609a38de7cb83c134f0f3d8b57ef291dde9024fd3d84cf
+size 2419599440

model-00045-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616112882e4075cb93f61c9a46088d3c38425eea7164886c1deccad68e2daf3a
+size 2690160856

model-00046-of-000163.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08e3931eeb44479c0a0d80aa377ec95557f88b02909cad501355264852c2a01
+size 2419598648