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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "Qwen3SharedMoeForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_qwen3_shared_moe.Qwen3SharedMoeConfig",
+    "AutoModel": "modeling_qwen3_shared_moe.Qwen3SharedMoeModel",
+    "AutoModelForCausalLM": "modeling_qwen3_shared_moe.Qwen3SharedMoeForCausalLM"
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 94,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_shared_moe",
+  "moe_intermediate_size": 1536,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 94,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": null,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration_qwen3_shared_moe.py

@@ -0,0 +1,230 @@
+# coding=utf-8
+# Copyright 2024 The Qwen team, Alibaba Group and the HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Qwen3SharedMoE model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import rope_config_validation
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class Qwen3SharedMoeConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Qwen3SharedMoeModel`]. It is used to instantiate a
+    Qwen3SharedMoE model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of [Qwen/Qwen3-MoE-15B-A2B](https://huggingface.co/Qwen/Qwen3-15B-A2B).
+
+    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 151936):
+            Vocabulary size of the Qwen3SharedMoE model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Qwen3SharedMoeModel`]
+        hidden_size (`int`, *optional*, defaults to 2048):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 6144):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 24):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 4):
+            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 `32`.
+        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 32768):
+            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`.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        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. NOTE: if you apply new rope type
+            and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
+            accordingly.
+            Expected contents:
+                `rope_type` (`str`):
+                    The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
+                    'llama3'], with 'default' being the original RoPE implementation.
+                `factor` (`float`, *optional*):
+                    Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
+                    most scaling types, a `factor` of x will enable the model to handle sequences of length x *
+                    original maximum pre-trained length.
+                `original_max_position_embeddings` (`int`, *optional*):
+                    Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
+                    pretraining.
+                `attention_factor` (`float`, *optional*):
+                    Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
+                    computation. If unspecified, it defaults to value recommended by the implementation, using the
+                    `factor` field to infer the suggested value.
+                `beta_fast` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 32.
+                `beta_slow` (`float`, *optional*):
+                    Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
+                    ramp function. If unspecified, it defaults to 1.
+                `short_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to short contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `long_factor` (`List[float]`, *optional*):
+                    Only used with 'longrope'. The scaling factor to be applied to long contexts (<
+                    `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
+                    size divided by the number of attention heads divided by 2
+                `low_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
+                `high_freq_factor` (`float`, *optional*):
+                    Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
+        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.
+        use_sliding_window (`bool`, *optional*, defaults to `False`):
+            Whether to use sliding window attention.
+        sliding_window (`int`, *optional*, defaults to 4096):
+            Sliding window attention (SWA) window size. If not specified, will default to `4096`.
+        max_window_layers (`int`, *optional*, defaults to 28):
+            The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        decoder_sparse_step (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer.
+        moe_intermediate_size (`int`, *optional*, defaults to 768):
+            Intermediate size of the routed expert.
+        shared_expert_intermediate_size (`int`, *optional*, defaults to None):
+            Intermediate size of the shared expert. `None` means no shared expert.
+        num_experts_per_tok (`int`, *optional*, defaults to 8):
+            Number of selected experts.
+        num_experts (`int`, *optional*, defaults to 128):
+            Number of routed experts.
+        norm_topk_prob (`bool`, *optional*, defaults to `False`):
+            Whether to normalize the topk probabilities.
+        output_router_logits (`bool`, *optional*, defaults to `False`):
+            Whether or not the router logits should be returned by the model. Enabling this will also
+            allow the model to output the auxiliary loss, including load balancing loss and router z-loss.
+        router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
+            The aux loss factor for the total loss.
+        mlp_only_layers (`List[int]`, *optional*, defaults to `[]`):
+            Indicate which layers use Qwen3SharedMoeMLP rather than Qwen3SharedMoeSparseMoeBlock
+            The list contains layer index, from 0 to num_layers-1 if we have num_layers layers
+            If `mlp_only_layers` is empty, `decoder_sparse_step` is used to determine the sparsity.
+    """
+
+    model_type = "qwen3_shared_moe"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    # Default tensor parallel plan for base model `Qwen3SharedMoe`
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise",
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.mlp.gate_proj": "colwise",
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+    }
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+
+    def __init__(
+        self,
+        vocab_size=151936,
+        hidden_size=2048,
+        intermediate_size=6144,
+        num_hidden_layers=24,
+        num_attention_heads=32,
+        num_key_value_heads=4,
+        hidden_act="silu",
+        max_position_embeddings=32768,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        attention_dropout=0.0,
+        decoder_sparse_step=1,
+        moe_intermediate_size=768,
+        shared_expert_intermediate_size=None,
+        num_experts_per_tok=8,
+        num_experts=128,
+        norm_topk_prob=False,
+        output_router_logits=False,
+        router_aux_loss_coef=0.001,
+        mlp_only_layers=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window if use_sliding_window else None
+        self.max_window_layers = max_window_layers
+
+        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
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, move it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self)
+
+        # MoE arguments
+        self.decoder_sparse_step = decoder_sparse_step
+        self.moe_intermediate_size = moe_intermediate_size
+        self.shared_expert_intermediate_size = shared_expert_intermediate_size
+        self.num_experts_per_tok = num_experts_per_tok
+        self.num_experts = num_experts
+        self.norm_topk_prob = norm_topk_prob
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+        self.mlp_only_layers = [] if mlp_only_layers is None else mlp_only_layers
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.52.3"
+}

model-00001-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9fd38a3545adf6c49487ba120794adc45d320959f7931e66b4a64dad0fe37b
+size 4609541672

model-00002-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323e41e6b1995960be63750619816d9a553a98de631bf6656ba928bb7d1ea00d
+size 4975511320

model-00003-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ae9ea07de48767eca8bfff1b36a7a2844868e90200748e51818e64abff2b0c
+size 4975511320

model-00004-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58de9d1170aab351ad1601ce569cfd2dd13ee9367bb85ff08857ac0a5d0deb0a
+size 4975511320

model-00005-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb13acf2168ec811ccc903e3cfb1ae2f1fdc39ff3dbebfde62d903db1329822
+size 4975511320

model-00006-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5733080e6e0d19b19a7eb793aee149f1101da93cf5034fd3a49d3ad80caa7ff3
+size 4975511320

model-00007-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3595459dfb48ff9646b113521554dc4e536d82c63b4234fa613f49ce1cbb433
+size 4975511320

model-00008-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ebe242f8bbb5286567fc3693cb04ad12387109ce0cca80ddb3f8b78771b046a
+size 4975511320

model-00009-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4bb2b679bc25e9d698e7650f2fe4dde9cde84392eaee96251b2f424f9c6aba
+size 4975511320

model-00010-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f25c5bcc94a95c3470486d62911e41a61d844aec29d4bb6260730c34673103
+size 4975511320

model-00011-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2781eaebc6b5a64934b67ffb0288d7c0a7b8f1732b106e101ae3dc8456d8f5d
+size 4975511336

model-00012-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26f14baced85f0bb9fc0dcf18229c6940a6d9424df03706fab39b7e15aaf3d8
+size 4975511328

model-00013-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d4ff1cbf7e4ae6ec3a0e15b2ea7c3b27c46aaa44cdf33d75c20ed56f57635
+size 4975511328

model-00014-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62cd354ed0ec3c09675623821e6cdcd5a80fff9743deebe5ecbadc9858415c5
+size 4975511328

model-00015-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7791cc6cf361c1637212ca979120582a65116ab5d4bf8945cb83f3918b241d
+size 4975511328

model-00016-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb72ecdb9a29417ff03ee19867daf4cd795124b6e2f284a763098cd18dabe9b3
+size 4975511328

model-00017-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ceb17aaebbcc02499e229a9f93192e0b656fd3e5e59db9497d413b83fbd0b98
+size 4975511328

model-00018-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4637b92ada14f33610de50a4d6529d8549df481392703b3d915e904dd2e90d
+size 4975511328

model-00019-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3ab6a61b52b88fe4547336fcf8b4d9bc293310bdade874cf5ab7f0bde1b0a1
+size 4975511328

model-00020-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76454d81a1a5ec69e4f1a8dd4ebd9f911137dad1660879f9533c007386df922e
+size 4975511328

model-00021-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8021572afcc2945354520ef60ba7642bdf40b54db106c51b273398e74c21cbd5
+size 4975511328

model-00022-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15e8f58b6b56c2ab4122d6d1c5937cc913fb65e08fb008bfc26ac92fc0fb564
+size 4975511328

model-00023-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ccce6c7f324c3a0ed210f58f8cf5670d7f607519a27f5b1070fc496d433c69
+size 4975511328

model-00024-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea2f12e4ea437d67037695356b90142a334c6acd5df21f6e2bff112794f8791
+size 4975511328

model-00025-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95c04541b074c26c18d81ee55bfc6dbe62e8121e9283e187f2578ae243ccd9e
+size 4975511328

model-00026-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7144e36cb3e495a47d96370b6059946b9c4e6a8c20b2018955772b55b2a337a
+size 4975511328

model-00027-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3906e8af289e0ddc84f32297ab214176f09caa6709437fc5ed588d29f420c67e
+size 4975511328

model-00028-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffd48bbe067b8eccb83d6a4b1232015337bf953d8fdeca713db8e4831a139dd
+size 4975511328

model-00029-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c0d30a39ce3af5ada2ca7c7cba88cdd7cd147b38a1b52f636130d29c8edde0
+size 4975511328

model-00030-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ae1399c68b2e4e8dea2b97fce64aa85d7122179547af72b1e7b61db5a88a53
+size 4975511328

model-00031-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1c413c32c1cf6017ca775906d7311e5e2e4f53c6e40dea15a8d6f9178e6db7
+size 4975511328

model-00032-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7057dd4181919c06bbca1c0b203e2cc448f6a15093584265cd0d308d98e131
+size 4975511328

model-00033-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae9ad195afcedaceb8cce509abd08ee004557aaf236312c53d388e2cd23ddd8
+size 4975511328

model-00034-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bea005f37c86e62e5586432487b484c47715394490322fc8502a00e79653a77
+size 4975511328

model-00035-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9443d308866d8cbb8f44bd5346d052b12e0d7f61db15c2d15ce8f5bad0ff1bf5
+size 4975511328

model-00036-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f784257c868e02377ac0b030f4ea32de10883535e72262a252c39eb6677e1b9
+size 4975511328

model-00037-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919a64aa4344463523b9b3d38f588781af849faa4bddb0e839be6908965d5ddb
+size 4975511328

model-00038-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d132952f4b47a9a921942f024f62e65998040d362656cc39f93d2d0f71214cc
+size 4975511328

model-00039-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c157863e5bc6a39fcea0c6d79b3b87badda1a9c4f20e9a60395af6be173832c
+size 4975511328

model-00040-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d4a6242647684d6cb1c3aefeb688ef8eb84d643caa5d37fafcfcea45ca04b6
+size 4975511328

model-00041-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c142dfdea9b973cf2720a0a40d667cf29922ccf27d796db84f7e65c9fa185ac
+size 4975511328

model-00042-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45be3f97a40b21e2dd99745603416558517245442f585a55915f1d60ba86f980
+size 4975511328

model-00043-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e76d65dd63c87c46be9e08e2df5662f2447defcb6d6e86a88e453f4b0a84ac3
+size 4975511328

model-00044-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a68b6daa0faa3e022d69f068499a117d66433dd38a986a8d89070ef2a506812
+size 4975511328

model-00045-of-00095.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f72d75eeedf9b07753355286bb4e37d9197e95f00b0887410ad31d657630eb
+size 4975511328