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

chat_template.jinja

@@ -0,0 +1,70 @@
+[gMASK]
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "Glm4SharedMoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_glm4_shared_moe.Glm4SharedMoeConfig",
+    "AutoModel": "modeling_glm4_shared_moe.Glm4SharedMoeModel",
+    "AutoModelForCausalLM": "modeling_glm4_shared_moe.Glm4SharedMoeForCausalLM"
+  },
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151366
+  ],
+  "first_k_dense_replace": 3,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_shared_moe",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 160,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 92,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 2.5,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "vocab_size": 151552
+}

configuration_glm4_shared_moe.py

@@ -0,0 +1,236 @@
+# coding=utf-8
+# Copyright 2025 The ZhipuAI Inc. team and 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.
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import rope_config_validation
+
+
+class Glm4SharedMoeConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`Glm4MoeModel`]. It is used to instantiate a
+    Glm4Moe model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of [THUDM/GLM-4-100B-A10B](https://huggingface.co/THUDM/GLM-4-100B-A10B).
+
+    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 151552):
+            Vocabulary size of the Glm4Moe model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`Glm4MoeModel`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 10944):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 46):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 96):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        partial_rotary_factor (`float`, *optional*, defaults to 0.5):
+            The factor of the partial rotary position.
+        num_key_value_heads (`int`, *optional*, defaults to 8):
+            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, check out [this
+            paper](https://huggingface.co/papers/2305.13245). 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 131072):
+            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-05):
+            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.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        moe_intermediate_size (`int`, *optional*, defaults to 1408):
+            Intermediate size of the routed expert.
+        num_experts_per_tok (`int`, *optional*, defaults to 8):
+            number of experts per token.
+        n_shared_experts (`int`, *optional*, defaults to 1):
+            Number of shared experts.
+        n_routed_experts (`int`, *optional*, defaults to 128):
+            Number of routed experts.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        n_group (`int`, *optional*, defaults to 1):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to 1):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        first_k_dense_replace (`int`, *optional*, defaults to 1):
+            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 `True`):
+            Whether to normalize the topk probabilities.
+        use_qk_norm (`bool`, *optional*, defaults to `False`):
+            Whether to use query-key normalization in the attention
+    ```python
+    >>> from transformers import Glm4MoeModel, Glm4MoeConfig
+
+    >>> # Initializing a Glm4Moe style configuration
+    >>> configuration = Glm4MoeConfig()
+
+    >>> # Initializing a model from the GLM-4-MOE-100B-A10B style configuration
+    >>> model = Glm4MoeModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "glm4_shared_moe"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    # Default tensor parallel plan for base model `Glm4Moe`
+    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.experts.*.gate_proj": "colwise",
+        "layers.*.mlp.experts.*.up_proj": "colwise",
+        "layers.*.mlp.experts.*.down_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=151552,
+        hidden_size=4096,
+        intermediate_size=10944,
+        num_hidden_layers=46,
+        num_attention_heads=96,
+        partial_rotary_factor=0.5,
+        num_key_value_heads=8,
+        hidden_act="silu",
+        max_position_embeddings=131072,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        moe_intermediate_size=1408,
+        num_experts_per_tok=8,
+        n_shared_experts=1,
+        n_routed_experts=128,
+        routed_scaling_factor=1.0,
+        n_group=1,
+        topk_group=1,
+        first_k_dense_replace=1,
+        norm_topk_prob=True,
+        use_qk_norm=False,
+        **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.partial_rotary_factor = partial_rotary_factor
+
+        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.moe_intermediate_size = moe_intermediate_size
+        self.num_experts_per_tok = num_experts_per_tok
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.routed_scaling_factor = routed_scaling_factor
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.use_qk_norm = use_qk_norm
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+
+__all__ = ["Glm4SharedMoeConfig"]

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151366
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79123a69917ffccee68aa1a970f806f06da209e1d5b4f970dc0bb66b901f095b
+size 5033164960

model-00002-of-00179-new.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60778aba79c8a88a43209961dd8005348ee2eacd8095f0051e5c10ddb5a1d52a
+size 3775057728

model-00002-of-00179-old.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8359b168dd5e58949d8fab8afec44083406e7548b7ce0718275304059a139d
+size 3775057728

model-00002-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60778aba79c8a88a43209961dd8005348ee2eacd8095f0051e5c10ddb5a1d52a
+size 3775057728

model-00003-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74134635135a8354cb4b5fde05c4289b630b11d06aa8194fe61da4107cf9ed48
+size 5033164960

model-00004-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e65f3aa6f5e21bd78e6a97be4f4c2a052a7b0f345b4bd7c7dca79b59035797
+size 2838088784

model-00005-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f223d5bddd4ffd4e350f4f72898daa5be8978f7ba5542509003ecd4995ff1cbc
+size 5033164960

model-00006-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb228e8fc3e514b7ab873d83c42446fd6ca5802cb1e1c2cd989e889c48ae64c7
+size 2838088784

model-00007-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ab9932adb791f016bff6b93c8528f8f74996b52e8117cc92181dfb5b77d61f
+size 5033164960

model-00008-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28697156d43819307ee1d0fa02d779f2ffcf3c934f44f46b2759a282a9bf6a2
+size 2838088784

model-00009-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5b9b574f4e6349e1384199d3b1af8d7351408c4dcf462234c598da3557b4ed
+size 5033164960

model-00010-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04863d35b35ad8701adfde10a594218c6388374227f9a0fffc9d64295e8421a
+size 2838088784

model-00011-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cada358281601b2a8dd353eecbbe4ae1b9e5c0567fb9f93641a7f401d5d4827
+size 5033164960

model-00012-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d07f3e6d40c0c0a83eb9136496e9ed81cf8c7c5b4f847537d5fb8f6c31c6e7f
+size 2838088784

model-00013-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33e6433919c4fe1cfb646e4348824fc6b6c186c6e654a4db5a93d8312b79c10
+size 5033164960

model-00014-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd6bdc77d90429a72bc3bb0901697288303d5547a95d5732f1ea0e668e6df32
+size 2838088784

model-00015-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c2c22d335c1e69cbc541105201d22253b9f9090b5f04fda4c4c989b6c6f117
+size 5033164960

model-00016-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c060b9471911f3090e9aa29f5e7f8f3f8b76b1ba62a4ddf8d2476628f6e0a0
+size 2838088768

model-00017-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45732ef503e5d5fa9281c9ed188c7d4b0d233b93e9d29f7d12a4369d23c16368
+size 5033164960

model-00018-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcfa47f48486787a6095b9e47837b5847b6d82a216f7492f3ff66d6d599d7ca
+size 2838088800

model-00019-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8e42f6f1875402c286d97853ab3f56a17f90a757e94818e266ae66e0dd4023
+size 5033164960

model-00020-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b6f0fc39c2b33c03f24dea8c0634ec6b3aa0004a994c82da6cd1956a09ac77
+size 2838088800

model-00021-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39940622f90bc8a9fac270bc35323166671287eef0da9b5aef838254397a9bef
+size 5033164960

model-00022-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72b815999fa325eb4128947f386ff15ca13c5d93463439d8c7899439da4e590
+size 2838088800

model-00023-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef86f6bdbd45444b2048eafb5a11f5eb99a0532fde854ba87e4c831d730a536b
+size 5033164960

model-00024-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd21e7b8ecb47fcad5b2bf4488c7e5ebb49a633f1b3ba54a2ddc8bfe905638d
+size 2838088800

model-00025-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95467ee13559bd01f13c549cc7d7df54fad1a8d821e0c772221fb9cdff3e7206
+size 5033164960

model-00026-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69249e2a9d3b66ffed534186ec0c731efdca91b08c334b04b6a5418a9899e853
+size 2838088800

model-00027-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3ac1f7cbe726da00a26b0fa95f08c311cff820cf2dab70747c05c1feaa2089
+size 5033164960

model-00028-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f205d269d8e2d0127bea2abe87c6539eebf4d91e15c9d080cb1f9d5c155cd3
+size 2838088800

model-00029-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8483710c95a36e8a6f16da9492bcd46fc3005e58a0fd138dc9b602fb4a10db7f
+size 5033164960

model-00030-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60520a7607729bfef0e7e85564939a8bbbd3fcc6b2615a7e0d0da9749e714fed
+size 2838088800

model-00031-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d538e1845ffb15b706515aade1ef52b3dd62886d98f614f75658c8ba124aef
+size 5033164960

model-00032-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ad00956c3bdda229c76d342730c6f4c1b29fb797e7f31dc23d663790b4d6e2
+size 2838088800

model-00033-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e1516229fd5865daa475b497036d90f81a0bd44900d2cd966acd75a78e24f2
+size 5033164960

model-00034-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c11ee29e0f6b5c24cbe93dd0719f56fa23786c5dc45c0516ee17ccf276fe3de
+size 2838088800

model-00035-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87328f785b040caa7b7c79f53a678a7f0620d1b9082b7a38d064133238ec1606
+size 5033164960

model-00036-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1674afc7afa0c344cdc968470b8e1f1d9555a9aa817e2a2ee6e78a193641aea
+size 2838088800

model-00037-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821a059310d43afb674191953d59e2e1d13d84eec728dde57811092ad8d44ffb
+size 5033164960

model-00038-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602e9f7ac5502f8ac9ea0c76fdbc7c87b41002ea1a792ddfa5da2de2b193deca
+size 2838088800

model-00039-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c811f06d0f869499e01bdd758e492f8fd1e004f33fa88b5b6779b9c65ed937c4
+size 5033164960

model-00040-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e098fff38872c1b865aad1caf20041b9f498ab09eac7a018e764445f3032ae61
+size 2838088800

model-00041-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2796a01ff697af30fbd028f32dd695ba5eda2b340b74868d7aa5a741e65efc9b
+size 5033164960

model-00042-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778ca06925b5df03eafddca304769d82868c7655e1b9dc3ededc19ce7d371288
+size 2838088800

model-00043-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29943ccb5570849225a1386f72066dd3e4e3ea8a7bbf2890ef428dfc4f246f95
+size 5033164960