Add files using upload-large-folder tool

README.md

@@ -0,0 +1,34 @@
+---
+license: mit
+base_model: perplexity-ai/r1-1776
+tags:
+- mlx
+---
+
+# mlx-community/perplexity-ai-r1-1776-4bit
+
+The Model [mlx-community/perplexity-ai-r1-1776-4bit](https://huggingface.co/mlx-community/perplexity-ai-r1-1776-4bit) was
+converted to MLX format from [perplexity-ai/r1-1776](https://huggingface.co/perplexity-ai/r1-1776)
+using mlx-lm version **0.21.4**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/perplexity-ai-r1-1776-4bit")
+
+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,
+    "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,
+        "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-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e639229d1b6326969e23508ec74894438307124b1464da91d534b92fa349fea
+size 3725148265

model-00002-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d9d3951da924734c88db61cab916d0b188ec0a9149af08ecb6178ef40dca76
+size 4361585379

model-00003-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58af6d9c927c6c4cd3ac4111b1f9bbe2f34e3ee998cbd14a9d560b0fe5d3adf5
+size 4227859218

model-00004-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682b62320a83b9ec3b013503d24a09454d7af069d3ab443984973c954b007493
+size 4361585451

model-00005-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd41bd51a7ca077abc20b4b57fbcba43f961525d010a079754fe9e2b16d4751
+size 4361585389

model-00006-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71ce6f760e6358c753fd674f5848cdad05f2588df91e97d3aafcf587af94bd9
+size 4227859214

model-00007-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda61469f2f211a06471ed0fff61b2a741bce2e4749c25dd75950ad07cf57978
+size 4361585449

model-00008-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d23350721bf31935f6fae692ed2b6a230ebe7f1a511a8361c120a63f7882b0
+size 4361585357

model-00009-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a897fca735014fc39a05033831f428d6d325ab0e6aa66e7d7b79777db0a8da5b
+size 4227859218

model-00010-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a454b1548858ec12d542d1ba3363d10b5998bde6d43cf1dee9a834072e3cdb2
+size 4361585375

model-00011-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc2a8a8fcb40415decee1ca63477741b541a8da06f2da7b3687f4ba75424178
+size 4361585378

model-00012-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b6cc3f701becbc26411c0cf106d19f9a4320b8223efee55fb35b900f2f9c4a
+size 4227859224

model-00013-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994fa413538d333166585af5c4895b4dca40997399f682b1576b189714ab43eb
+size 4361585461

model-00014-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef54d46f9ce3ecbb1079203f784c4fe1a15c0e6b81842ec31e980544abe118d
+size 4361585391

model-00015-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9444b6888ff98d285db4a9b8fa220e3195f071c0e04b54a4d4aa9305808b4aeb
+size 4227859224

model-00016-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125333db5564bb1c428792e8b4983397a94e02d6ff188530783fcdfc3e4bb13c
+size 4361585455

model-00017-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae3be5eaa43a10971f7a513071943ba2b4eb97ab9b9149809ff44e342a9b3de
+size 4361585389

model-00018-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f022d9143e523cdc053097758e9681222b8947d42b1b56714bf47b3a1e2f28d1
+size 4227859220

model-00019-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d12944cd71da28faf6a6ed48e23feca9d4852290210d52e5922c0c96fae8bea
+size 4361585463

model-00020-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a90594e220af850716a6b68720dff03912189b158ed9f99997ade77f21491c0
+size 4361585423

model-00021-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22f259ff92722c7261f536cd8a09209d15d3f17f6aa1eeaab59b63e4f2f517f
+size 4227859224

model-00022-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085788266a9b98e950e0b1205c6c5b6508c1bbf7e62ec86630fc9a4bc5e19b27
+size 4361585441

model-00023-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d07cb7fa9d47d4a45f840231116873f836d321e883dd027b9d13ae93183fa9
+size 4361585399

model-00024-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe8e48763ccbe3dde8d90ba3418e09015524f07029805b70def70f6e92131cf
+size 4227859226

model-00025-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6eef7d3b164272fd8cac3ebe5f6b65931b3aeecec775998b36c78e728727289
+size 4361585485

model-00026-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f831530ddcd057ab5065a1e21a631688052835b92c6f49a98aadb77de51869d
+size 4361585403

model-00027-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f55489f72bc1624eb80c8a8118a298ff44071ea60d394a6ecea996ba3ec997
+size 4227859220

model-00028-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658eb03606209b77f7a4aecf9eb0f5ecabb547b4c41119a56e0911642f526302
+size 4361585453

model-00029-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91735a364a3209acfe7c0ebcde2bff6d48ab0e3f205e7a6033a19f03dd1170e3
+size 4361585371

model-00030-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15075e8af6989ec6d5e69b2329ac18da47b71fbe1000e81c45c73dcccd16b4a
+size 4227859222

model-00031-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ed4a0e523de336e3d9f15101ea7b4260690bb22cc7d2063abb8bc3e331e064
+size 4361585487

model-00032-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d0c2639dd988f87ee532535765f4e1bfbf8a21975fad6497e926919bf0b80f
+size 4361585433

model-00033-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fc7f3cbb8dcf5df674d9c9ac98acd732c19896b1df03215d484af8bc056cc3
+size 4227859218

model-00034-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6027c64069e5190aa41e11627bdb0a72a5a272e4cf7d641800a7b04a558efac0
+size 4361585441

model-00035-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbdcf03f1e918a1d84a65cb10d92c3f8338d43e2397b1913fc0aface99f6f1b
+size 4361585411

model-00036-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dba7a707912b50afd4af3d1025d1d40424bc7aaa39677a985688b5bfcd62f8
+size 4227859224

model-00037-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad22deea3e560c7d9532e6b2c5377b33b1d44cebee10079368786f898c107af1
+size 4361585487

model-00038-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a9eb8010a09f05add02fb0f2068c59c47fcf9d3f0f36422680cf641b2e5e06
+size 4361585399

model-00039-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e134db431f9d807121efdd221d803c58e4ee50053f28ab7efdb7c73af74c5e
+size 4227859220

model-00040-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5b8df0ad5b16bac8ed2879467f138129d35c5a080b1f0b540afe87131834d7
+size 4361585427

model-00041-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85886a431f6897c363a7b1b7fecc481e3e74cc616838ee8951367d703b3b3e5b
+size 4361585389

model-00042-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67f008d5c552e65c7ff92fde2a108ea705da648ccee13aacfab54755e6dcbdf
+size 4227859224

model-00043-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c5d3ce8bee94905cf22130203376fbcf272ae20c3893b0230671686849c235
+size 4361585485

model-00044-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca58e249a28a09dd47b59b11bc487578ae41abaaad1ea325a4602b53212263c
+size 4361585425

model-00045-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c2f3661644687257b2398001540a5875e267fadb831e9f684c48e56bbe9370
+size 4227859224

model-00046-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d93b78ba54e57def62c45d80cfd53c1364f4d180e838c17c03a2ead1b259e3
+size 4361585485

model-00047-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8391ba9b4a021378a44a5d2d44c48291d3a5b402c7b907d0223ddf851997caf7
+size 4361585385