Add files using upload-large-folder tool

README.md

@@ -0,0 +1,36 @@
+---
+license: mit
+pipeline_tag: text-generation
+base_model: deepseek-ai/DeepSeek-V3-0324
+library_name: mlx
+tags:
+- mlx
+---
+
+# mlx-community/DeepSeek-V3-0324-4bit
+
+This model [mlx-community/DeepSeek-V3-0324-4bit](https://huggingface.co/mlx-community/DeepSeek-V3-0324-4bit) was
+converted to MLX format from [deepseek-ai/DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)
+using mlx-lm version **0.22.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/DeepSeek-V3-0324-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,69 @@
+{
+    "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": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 40,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 10000,
+    "routed_scaling_factor": 2.5,
+    "scoring_func": "sigmoid",
+    "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-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420cefc97a209bc7dca275dd0323033580936bae333f040de09259319ee3d6d2
+size 3725148265

model-00002-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d56c3409710f0df7596a5e8b084224eeec1a567c5ac87c2889eaef15d78751
+size 4361585379

model-00003-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cea11170512349c000d6922c83cbcc59c4735a801ee1c51c2f55c22f5af23c9
+size 4227859218

model-00004-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee031183293964e596ff4ffcae51847f9a1f8121bca7b03347eab77bebe8d7c0
+size 4361585451

model-00005-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c43bc467be082473d871d806baf8a1e1d866e3a5ec7bb032945047e84c0ec36
+size 4361585389

model-00006-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47e3a1a828af5394fd488e47c7e4c61e7bb101bcce14648018ee650bc1e3aaa9
+size 4227859214

model-00007-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fec87142a75484037bb6892ccaaafe9d94d20dddb78404d5af19e0c0dc970c3
+size 4361585449

model-00008-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10991df4887105b227de9a8a1061d8e23742c46399ad21122fcad4044c9bd1f8
+size 4361585357

model-00009-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266eb4800b3c1770d17cdda249d32ebb59a53640cd5bd918859576c7aa7bdf8c
+size 4227859218

model-00010-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96f79d5049a4a12fe0d429798d6c5bfb7e2826ab978edef420df076e315bc4f
+size 4361585375

model-00011-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080f4862600e2dbb3039560b6f09ad9df483d98dd6f872a1e1c1c5af34eef2d4
+size 4361585378

model-00012-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a5be6328390fb55ffa385bb963ee5de5f7b9414f65fe95ba2953dbf2d08d9a
+size 4227859224

model-00013-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441c68041831a3c63e7824d20cbae014b7a742572ab2cfd1bf10ad7a63a5e72e
+size 4361585461

model-00014-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e5a4209228dff14ab65b23a9738f99acdb18e7fa4e4b50c1a0b87dd6a24c30
+size 4361585391

model-00015-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8a52bf69a23ed355c9580dca55a77f3f04538a8255794bfaef8b7d0ff96e58
+size 4227859224

model-00016-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6181a065940f73c9bbeec2e9960735734ece3ec3f8a6d522b6c2e7337c435b
+size 4361585455

model-00017-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0515fdd973feac7c3cb7ae6d777b8daed28ec872044bfbdbbc4a40a05c55f4
+size 4361585389

model-00018-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9719ce5848382650ae4a8aeb66632617b862ddceb921a5774522c650c7bc0412
+size 4227859220

model-00019-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5785a9d86fac01fc683c09b53f8b3eabd011e0c598cb15cdc4381e996d798b0a
+size 4361585463

model-00020-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca66fe3e628db32c083934efd30eeb29464628535bfea25d9e47ac1bece553d
+size 4361585423

model-00021-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2894009b4a34c0cf3882c3d386486162f3713c2bb399fd1ed895d7ec27002c35
+size 4227859224

model-00022-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380fb312d00798273edecae944448fe553128c3e938f997c53cc5c04c1c08e2a
+size 4361585441

model-00023-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb77a4ba2977f0e23edbe7c24b3439ba7d2bd2adbd836905658f38037d745b5
+size 4361585399

model-00024-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56cf785ef9cc09c0e2ef65b05d0232fcbfff351d46fce99e3c41a8ebce22652
+size 4227859226

model-00025-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e9ec21964726e9d573bb61d7e9263d4b4ee53f2ee2c77d42621f75f2155cf1
+size 4361585485

model-00026-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51453015b22b1f08bb7debc9ff9ebc2cc6be6cb4ccb46c7c73257a06abce16fb
+size 4361585403

model-00027-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbff7e32eca4c4d17b5f1db7b6c469acdbf43be2107ab45840d68fc750a67e8
+size 4227859220

model-00028-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65b05bba4495102a59ded3c52f5f5aded4e502dfafe56700e34b0ebf859f0d6
+size 4361585453

model-00029-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81f9a30da7ed8182741dd13736e34f905a96a6cb2fcd97c52bec63668f537b6
+size 4361585371

model-00030-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7facbce0cb6519947195268bd39489c53b9c9c1cb6b22d3ac2315e31d39247bd
+size 4227859222

model-00031-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76884c6e1cbf8ae2ec6abe1cc59f6db83e78e1e9a095eb64587c87731790b12b
+size 4361585487

model-00032-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324fc661a86eb6be2e704c2cc0ef37378ac453ddc53967c9d3ce61e50909c8ca
+size 4361585433

model-00033-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b8a9063ce5d06e4141193a98f206cd8419cfd51a84ede7ca4a756e9d896223
+size 4227859218

model-00034-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67d2eff1f740301904678fe5d766170db4d4c8d517e85cc6782a06a6be9c677
+size 4361585441

model-00035-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5275be52f00466d3a7639e5b34a47b4e4897fa695c71f4c1c5f23e8ba46bb652
+size 4361585411

model-00036-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d557b4b7e21d0224cd1ea6d0ba9ab7ff6e5de139321dd3ad3583275579b3bf
+size 4227859224

model-00037-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f3440118ae6f9f417d3bcbebba13f786752ddeec3ea781aa553fc94b9849bc
+size 4361585487

model-00038-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deace3371631e6468aca15af2feb48628ebee1c5990d394dcd94038fd06a798a
+size 4361585399

model-00039-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec3310aa068f5d30e3ee614b7a1d88e004a3bdd393789cb87e8ddef3f93f7c9
+size 4227859220

model-00040-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b999fd7930a1b4b33abffca1a6ded0cdb1c2b3aa6c3eddffb8463e7240165df
+size 4361585427

model-00041-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712ac11db9b1ff9a33b2ff52ffbe33b292086afb14d014f016d8688ccaf7c708
+size 4361585389

model-00042-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1704dcda42501339d011dc664757788229038fac892e76d53a41a52476872304
+size 4227859224

model-00043-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1e386a0f57df0a9ee07fd4a2a6acb564dfa0a2fa2470212275c7e23d61b4cb
+size 4361585485

model-00044-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd4888d92d61acadde651e92c2430d490f19be6921c0bd1e4fe9ccaec90294b
+size 4361585425

model-00045-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b18128aad03c99ca7ff4c968963c46eeb504b815b3a51c9b749e9f0a4f8304c
+size 4227859224

model-00046-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0817a48bef8ed600c641471784f7edbc63b83f42af1a2c6480febe5b4daa2663
+size 4361585485

model-00047-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47e9ad4964efed79547703edfe3af61f76e6bef03aab0f72ad9af9716f01af9
+size 4361585385