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 +1,103 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{{ visible_text(m.content) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,48 @@
+{
+  "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"
+  },
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "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 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342c1f2d267f073e34ebbf09b7aba09266b874fa762995d0b393e0550c851e97
+size 5033164960

model-00002-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d34e655aef934f37bce12187fb973d90d655a6f135eddbf71e3d503d22f8bef
+size 3775057728

model-00003-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48b6aa05cb17f13981845f088c8e2e6b6daa89e345078cf30fbb5905e5b2456
+size 5033164960

model-00004-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b44902125fa0294aaa35905832ac4decbaa116898133c80e9b1f87caa1c3ad
+size 2838088784

model-00005-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d78d534b34a2ef488302e9b91e6f8cdc6e2f96dcb3b2dfd050ddf7d3e587a9c
+size 5033164960

model-00006-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a28a0a80c918b089ae5e4873102d97682d90c779f39c9fdbf8433c3f8991e88
+size 2838088784

model-00007-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48963fecb1cded9bd1023247a6b48551885bc50853af9a1f0e6ea91b59597e3
+size 5033164960

model-00008-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c85509b5f3bdf6993d933b6304d0b0c94fc7ddc9d27655f59fcd95e8a5241fc
+size 2838088784

model-00009-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ad233d52314a4c8b254a1c4147029c46fc027bc337c82e69f8affa6b4a931f
+size 5033164960

model-00010-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d18544ef286c16b2e4a48d1a6ec19f98629b7e081cb50097d7911f1221440d14
+size 2838088784

model-00011-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def92abe9e6b8476a1ecf925d31667ca88b0380d3c4f346c1d3dfbbebc17a6c3
+size 5033164960

model-00012-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9acfd8bbb947385c869106c35979e6a4836130586a80c3cb56450da79d25490
+size 2838088784

model-00013-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a906b5acd2be14b538376d409b41985a5622afd4721b164b66df788d56c5d4b6
+size 5033164960

model-00014-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2acf8f5ff4906da6ed1fe151b40245402fce23391aee75a2b5c222b1367a95
+size 2838088784

model-00015-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96ff7e7d03e4eed163c41fb8150ce7d8f246893bd17d1130b8569a6f1fe733d
+size 5033164960

model-00016-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a00e5528cbed1ec503c948a5c7e23ab78e04a05f0c8be211654bb5568cc9e4
+size 2838088768

model-00017-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a52b193546cacdd4aee9305b94f3aeabc0555997840afaf4e94ca8d0f388333
+size 5033164960

model-00018-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f13a6bca1095ab22bc9ee7f93355f7bf5dc5a1b759ff1c9019a7152d82a406
+size 2838088800

model-00019-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05b71e3293d5295f65a04ee45e6651d42dad82b6c483455c818834c117d8a4c
+size 5033164960

model-00020-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2851d8eecfc487e90f83edf3ead87cb516eee5a605e8934995c432657126ab34
+size 2838088800

model-00021-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a10f3b0533a607eda2505d0746da51ad5d7c22a01c5da483bdd0964acdc1c1
+size 5033164960

model-00022-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3bdfcbc2894acc38ea7d1de7caa6bbdb69e7536ad53e21f5f54925090c8093e
+size 2838088800

model-00023-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4b52077979cc5e7c9f2cadfd97ddc96e524bbc587e81a4ee3952ce88b1bee7
+size 5033164960

model-00024-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717dc4b7873bb50dd157c50ab9342919b465db35d8a5257f49565d74d76d7476
+size 2838088800

model-00025-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de8206df555915203d5482c5cd3dec81024710f8a5444df1ff5d0cc4e1a2d68
+size 5033164960

model-00026-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a355a140b2be0deb38c80c6fc6cf70b2e546af709b42cc6d30c311c4bb657b
+size 2838088800

model-00027-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c835ff3acf37e41e609f10f1b79cb4d97b0847c956bc41aae3009f208bb02f
+size 5033164960

model-00028-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92f61a7dc39a9e54361daa9fd96cc6edc87cf079b28f410f9a90c3fc361a852
+size 2838088800

model-00029-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeec0f43399352e8266f80fcc295f80dd10f8eab73682cc711b002c78193df5b
+size 5033164960

model-00030-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55aabbc5ed5fc460a60d7d37588381ea99e74a371ad15b685d253986725f69e1
+size 2838088800

model-00031-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e155356a500bbdfaf1790305ca471e31a9ab9d4ece9b2c6b50158d47d67797
+size 5033164960

model-00032-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98732295e88022f13a42698b347e1a254fd6791d838bf1a4229506163486490d
+size 2838088800

model-00033-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b53f771c9351a628502f635d20c08725734758ab06703da6991b065e3576ac
+size 5033164960

model-00034-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43103ebd7877d8752ac42c585712904d19ecdb74b7ee363f4f9dbbfdc957388
+size 2838088800

model-00035-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3fc22f152ca7393ef6d45e25052638baf0fda4134eec342ace8a6a65de8cb8
+size 5033164960

model-00036-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c1de44fe42779ddf79a2a24ca91373610a7a8e6ab96527d00f13ddf95657a1
+size 2838088800

model-00037-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2801226d0fc28026e053e0aea3c2dc2c199c0aad15528f9a5c37762cbaa95a
+size 5033164960

model-00038-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28be52e6665fb5fd9913bffa54ad4b8af05a4cb503fdc076a29eacd25979faad
+size 2838088800

model-00039-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2cbb9f9cddd9e22b284ee670f58510809b0be528a3e709b9b65cef4a23b0c2
+size 5033164960

model-00040-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd9031b29a6c7f320369203728eda17b9a8f706f03cde60a31ffcbacc73e8f9
+size 2838088800

model-00041-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d339c1177b1ee3e609f2537cf86e71f7499f06c0a1846c7a821c3ccc50fe6500
+size 5033164960

model-00042-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b157d807302adc3b82e71703a143885af70c6e66b8dc2c752d772714a2adaad8
+size 2838088800

model-00043-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff5e89421ec82f7fff115eea0c8b21209d28dc0e8b04356254ef3a99f2ad766
+size 5033164960

model-00044-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582cd7cbf32daba2d55cc1d50811c8c56f229eac0745503fa5291fbf75a6010c
+size 2838088800

model-00045-of-00179.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16a2a6936976c2b95409a8829f9ccab45057f142bac0c184c66ceb4e50b69f9
+size 5033164960