Add files using upload-large-folder tool

README.md

@@ -0,0 +1,21 @@
+---
+license: mit
+base_model:
+- deepseek-ai/DeepSeek-R1
+---
+
+# R1 1776
+
+Blog link: [https://perplexity.ai/hub/blog/open-sourcing-r1-1776](https://perplexity.ai/hub/blog/open-sourcing-r1-1776 ) 
+
+R1 1776 is a DeepSeek-R1 reasoning model that has been post-trained by Perplexity AI to remove Chinese Communist Party censorship. 
+The model provides unbiased, accurate, and factual information while maintaining high reasoning capabilities.
+
+## Evals
+
+To ensure our model remains fully “uncensored” and capable of engaging with a broad spectrum of sensitive topics, we curated a diverse, multilingual evaluation set of over a 1000 of examples that comprehensively cover such subjects. We then use human annotators as well as carefully designed LLM judges to measure the likelihood a model will evade or provide overly sanitized responses to the queries.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/GiN2VqC5hawUgAGJ6oHla.png)
+
+We also ensured that the model’s math and reasoning abilities remained intact after the decensoring process. Evaluations on multiple benchmarks showed that our post-trained model performed on par with the base R1 model, indicating that the decensoring had no impact on its core reasoning capabilities.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/675c8332d01f593dc90817f5/n4Z9Byqp2S7sKUvCvI40R.png)
+

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1,
+    "mscale_all_dim": 1,
+    "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": "4.46.3",
+  "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,
+        )

model-00001-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e42946865f05124b81da4d864f0a0b453c8e6c838f1cb3771c894c0bdba2d9
+size 5221572256

model-00002-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a602965ac1a2dc7e32c6ecde2cf1bc7550d2edb29e0bcf312c6f452733161c15
+size 5239421672

model-00003-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0dd4e75062d0dee2411ed7acc70b2fa8fcb71a07a074c713719e90b9c2831e
+size 5239421688

model-00004-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88058cedb5d83669febf9f375a38be100101e56516c9a6287cb3fe384190fcd0
+size 5239421688

model-00005-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133b2154b4322a66b9108f52a383e3c6248f1e1c3bf801dbf4e16d3464ce1bf1
+size 5327877256

model-00006-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b704776e2453341487924ae324d2ec7c215fcae1b6c51261c90c202c6aa4cca4
+size 5347233168

model-00007-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1a747944d96a8dd00d74ea3bdfda595eda641dbe5791f559156377a16e5685
+size 5343565976

model-00008-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae80732437f8f45b7413ffb5c12844360139c80553f058c7be3a683dce181a2
+size 5343565856

model-00009-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac02b443030a85b54884690bab573922b86ceaf2ec730ec44d8a278b4a1fa72
+size 5343565976

model-00010-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86d9b286f37dcb5126083dcfdd9ced2518afa91eee9ef5cf891cbb85a7abace
+size 5347236104

model-00011-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f31b5c0a6b020309c182400199f4e3873da063655706ece63a21c5e4f31336
+size 5343566056

model-00012-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d0710ceb09cffe7b4ad36f3a783ba1760fd6b529c4abf4abd09593648b91d
+size 5343565816

model-00013-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132cda274e9fcf9d7043c8f9bee71f976612f681a3ee14924ca8f187bfc7e267
+size 5343565976

model-00014-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27df433a3aabf2bd444f04f48984e0e2a8bfcb8be9ef1335f6c94226e2e5e7d5
+size 5347236088

model-00015-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001ccd43ea6e1e8313aefb7cec99c403643a53c474a121d25cd96573907efedc
+size 5343566128

model-00016-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04061719e0f5e0811b45d1da696f7c4e47e7608e16eda4c405124f3f8acca8e5
+size 5343565776

model-00017-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76865c832dd96ae53d696afbb79ceb57106fcb21be3c2ae7ddba773e45cf458
+size 5343565960

model-00018-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3ccce5954d8775b702a6339466f398c40a926a2f06db5dfa192014d264de60
+size 5347236088

model-00019-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2fec0ac7c357f1221f20cb87b267b7d7e841f1e3e216139050bd63468d51d4
+size 5343566096

model-00020-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ec440cb8406c25021f8adb962dbbd0ff61d272e38cb6e8d9b53072c2908028
+size 5343565856

model-00021-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097ebb4cb57ab272955d1986cfb058200634d370de40b2ae2cbb616c04cdf5c3
+size 5343565920

model-00022-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28abbeeb183cb57e1b27a3f97ccd8396dd32f59fc47e5783b1986b093e80c0b
+size 5343565976

model-00023-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c009b50b74ed81462dd0a6e90a5746bd34fd44239690321705a322312522a3cf
+size 5347236168

model-00024-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c057e95c5be5f4c58aac4f6324fb3ae502cc96e1f062dff8eeb9954ae390f3
+size 5343565936

model-00025-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70761163c509f2d1a46f9fbca7cca2500fc94e2599e1c39bea49ad3270a766bd
+size 5343565880

model-00026-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf430d04703caee6cbaef69b2e47bd761c02e173252c99318cf01bf9517b3dc1
+size 5343565976

model-00027-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc093a88ef7405786eac7eb249d47e6956132aba896dbad1b67a8c1d52852e2
+size 5347236128

model-00028-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586aebb71f40271ca209d6c298e54b0d249e1f3e80e12b9218bb08816d1fe5fd
+size 5343566016

model-00029-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5431a91ef81dccbd103d9f5923eb4d330f55dd2e832337ec43c2d9284f6ca297
+size 5343565840

model-00030-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3089c81223ec3ddf77c6aad16798e9bca8c916cc28906a13a343e4d2ac12c21f
+size 5343565976

model-00031-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61995e76bcbfdac7e3916c9a929fca8451fa1941d4a6cb7fb56e31f70df02e6
+size 5347236088

model-00032-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff57686d6e4537b596b57c2e123ebfb25c486fbaefc4b02b37306576e25b614
+size 5343566088

model-00033-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771f69118ee8775c8b1c9972f8e29ad5412205c44a41871f42857a16a9e4b58c
+size 5343565800

model-00034-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc13630f84b1abdbd2a4f9275c1b189466399a9ffed1e3b757f7716deafc03d
+size 5343565976

model-00035-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3eb21edf196deb83969b0b1e678314d137d337ef44c5f7279f77c7d72649008
+size 5347236144

model-00036-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94dfcd873880969b2669367e830610215e2e76b140c314b454c81f02161f7c75
+size 5343566296

model-00037-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14192c93a026510dc828af82202a046d2ede22fd2ab6306746b5dc250ead2008
+size 5343565992

model-00038-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c832e557308168e5a62fee4350273e073ea3765e0b4e4ee86fc81b3ba807c3d6
+size 5343566120

model-00039-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3caac8069937e15d419cd5380c94094f0c20a3fd49f40160726cdc57f5e53398
+size 5347236272

model-00040-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee364cc2d6dd0bf45048084e9c90aad4a562802ed9db8ccd6970e6752a4cbd1c
+size 5343566256

model-00041-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a5615ed4d7c529334cfd0ae4338aa50959dea74032dab472e6f7cfd45ebad6
+size 5343566072

model-00042-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b504bfd77625e9dbf2e2dd39fb6dd67f71027451126dc4b51c22ee3a2fedf02d
+size 5343566080

model-00043-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c55a92723618a78c464363a74c1c94e481417a3621536339d510fc1cb9b8f81
+size 5343566160

model-00044-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52eb44136dc20a0afa8f9848b39dd385f1b6fa757ba53225654f8e82fde8d46b
+size 5347236328

model-00045-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b17bcf67ecc59f3880cb131036fa72764b09f2455ec9f4f945cd74e5c98684f
+size 5343566152

model-00046-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30eb2349427d0eb60d2e52f9e5815a92331351c370119988d32952dce13c7963
+size 5343566040

model-00047-of-252.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2cb67b6e90ded2890171cb01938038783dc02e098e991a3570c1b9c7a100003
+size 5343566160