Upload folder using huggingface_hub

.gitattributes

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

config.json

@@ -0,0 +1,90 @@
+{
+  "_name_or_path": "/data1/DeepSeek-R1-bf16",
+  "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": {
+    "amp": true,
+    "autoround_version": "0.4.6",
+    "batch_size": 4,
+    "bits": 4,
+    "data_type": "int",
+    "dataset": "NeelNanda/pile-10k",
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "gradient_accumulate_steps": 1,
+    "group_size": 64,
+    "iters": 200,
+    "low_gpu_mem_usage": true,
+    "lr": 0.005,
+    "minmax_lr": 0.005,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "nsamples": 512,
+    "quant_method": "awq",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "sym": false,
+    "to_quant_block_names": null,
+    "version": "gemm",
+    "zero_point": true
+  },
+  "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": "float16",
+  "transformers_version": "4.49.0",
+  "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,
+        )

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5506303aa8607923359cacc59cfa5db99719300623c0e1d960569b13d32e554
+size 4995076312

model-00002-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7b9b2c091b4c73b0bba611a92f6dc53c9b67e4feb54feb5c3603d1dac9728e
+size 4995320096

model-00003-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957d566962af8c7987876afa201be552919a251b63f28785018b3f9d428be79
+size 4993632760

model-00004-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3469507216a7ea7115bac7c2e1aff1d9cabd493e63e8db0f54bf6087afca337c
+size 4995319632

model-00005-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd47e23f0d016efce35d594cdf216c6f65ffa2f04add7e39520e12c6c3de35a
+size 4995319632

model-00006-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d15f1c8d242f63286fa1f6531fbcc8723b8ffd3ed61461692ee32fcbba2d44b
+size 4995319680

model-00007-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25b001cd75c4d68cc805ba27cd4da3593a4f64a3e501ef0a392b9a014e6db00
+size 4995320096

model-00008-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ba920df80488b45375843fbf8cfe9f8fdf111097d0ec229a6dff2e2c8b78a4
+size 4993632816

model-00009-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64bfb7bfca2ed08f379a385c9312a6e05b51f3e926fe057e83b88a3b0c9e92a
+size 4995319632

model-00010-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c602640f3987506664e2d3bfd7ac5d62134a9e4d02ce27f2a056d3cded72f390
+size 4995321024

model-00011-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb3c1f639f3d71bdcf64a9ab5702426f2bf85c1b24b5ab20e1625b7cba5d0f8
+size 4995321512

model-00012-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1797a8d31fdf885c1fc48c20421b16d2b13402f16b68899915097bd1143e89b
+size 4995321960

model-00013-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7e286f92e4240d8ad8c90424d92f0244b4b43d35cc02229f2a7541194bcb41
+size 4955755456

model-00014-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30afc28393d49d933fca35ae95e0ff19603827ab08f9a444c42af46988f0f7e4
+size 4993631600

model-00015-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762591da0527a6e0847d0ec6139896e4767dc6f6dd88437d5ef26d8dead2dde0
+size 4995321512

model-00016-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f84bf690ebc47d0eded6630ffed4f7448b893ea70e9c095f9c1d6a16e563dab
+size 4995321512

model-00017-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f778063489904393240ff584f893ee6e307be742b0fda76533923dd9188c9d
+size 4995321920

model-00018-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533fe4c3ebb31c9ad6531de70c8e04cbef2a3517ad5f7ab15dadc027be3e209b
+size 4995322024

model-00019-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb00f8787bd9faa5d7f8f120b584366d2105ecc2e77d28104768d3067b29616
+size 4993634296

model-00020-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfd4ec4f57741b06a20ac2a4a48ffcee4403c78fc4b742bad28516a77e6443ab
+size 4995321512

model-00021-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ec4c3eb605975b0438adbef2d253720aa2ae192eeb5797b94fa7ef3e6a4fc2
+size 4995321512

model-00022-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82b4318ffeced715c661160554c1ad7eaf395f6290fbb006cce097e04a0a6ad
+size 4995321864

model-00023-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270060e197e9c0eb513e2ac594bd08bf0a57926a7d30daa87f0a88c4f04b37f9
+size 4995321968

model-00024-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08212ecd370f74476dceec1c40dc1d5bcc166da7f0d49fa81a6013a858899fd8
+size 4993634408

model-00025-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96eadf29a24b240db3b1e8899f0e1d186aade47d3eec430662e1117d20dd57c3
+size 4995321512

model-00026-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af5d9a5dea4d25d96eae628ee00ecaa62aec79220af48f585a82c49be33f15a
+size 4995321512

model-00027-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28e1a055eddf0b2543e8333d1a39d7423a546c1559ff728d09569a704c4c5f3
+size 4995321808

model-00028-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba1fa1abd1915fd028ed88cd1e07091027abb050c7eeb0ba0bb8af0cd0ca57d
+size 4995321968

model-00029-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d58c73708bd03a1152a172687909d0da9d773614a5be29f7f1cf2d4bc405476
+size 4993634464

model-00030-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90db5e0193419b6a582bb97a22986e736721856e5cbdd87226a0347e4267b62c
+size 4995321512

model-00031-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a9a25139ce508f226b4ba10a458715cfd8c24a5a9d7d225b1584c49f58d7d5
+size 4995321512

model-00032-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16d935f2b69c0da31233a21e8126fb28f62c261cb9fe945f6e18e1fd1217011
+size 4995321744

model-00033-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca092c170932d63c65e4c33afaada494b1b25b1e46d9e70db00eaefbd3480d2a
+size 4995321968

model-00034-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3798aab27fe3843c6ae0b61b16edd9e88bebc9368c828c4124770f6d40b6fd89
+size 4993634520

model-00035-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b270f4d9629ffce07f2d1766e7128d510afcf7145037d7e339a0231b5abb92
+size 4995321512

model-00036-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4f2ee2ab7b04f58dfe7ac7d86dc3bb29e5119990fd81b5bb4ed051506451e9
+size 4995321512

model-00037-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3022c0b1779486ed6703e9b95d22b16ad5757f0e50994749993122098fa11bf6
+size 4995321688

model-00038-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c7418fbe9c893c649c8610810391d1906ebd0087a755520b5c83ceb80d9518
+size 4995321968

model-00039-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8ee8ff9e0cfe475802edef127dab3431f2f83983f717b3c1a0ce9ce245f3ce
+size 4993634584

model-00040-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81de3e1c0c21041a9ce515e58751afd330c19f76d8b48741f6bcd0cec8232359
+size 4995321512

model-00041-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0ee4377bcd58c3df3645f7f8271daf47593b06794f03df6cfe9803e3729262
+size 4995321512

model-00042-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8fa059a5bd50d3418d9c5d88f3eaf1c444bafdb8d1462db89b2d549adcbe02
+size 4995321632

model-00043-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7a87eaee506cc174f05d5a40867548f3c29d92f98c8e4649448d9a6854ae6d
+size 4995321968

model-00044-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc55903c9d2f705c2c209aeb06d50e3a9e0a455253e5d9060520edcf01aba807
+size 4993634632

model-00045-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c507f74f1abf3978826abf0b8ac608f8a8d5ccf6d4dc97cade73fb930f72e3
+size 4995321512

model-00046-of-00074.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8c27d1fb9cf07cd7776996a5d7a471eb8f7322ce3cdc1a702ea8623d3c244e
+size 4995321512