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": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_shared_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "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": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "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"]

convert_hf_to_scm.py

@@ -0,0 +1,126 @@
+import glob
+import re
+import shutil
+import sys
+
+import accelerate
+import torch
+from safetensors import safe_open
+from configuration_glm4_shared_moe import Glm4SharedMoeConfig
+from modeling_glm4_shared_moe import Glm4SharedMoeForCausalLM
+from transformers.models.glm4_moe.configuration_glm4_moe import Glm4MoeConfig
+
+input_model = sys.argv[1]
+output_model_path = sys.argv[2]
+
+auto_map = {
+    "AutoConfig": "configuration_glm4_shared_moe.Glm4SharedMoeConfig",
+    "AutoModel": "modeling_glm4_shared_moe.Glm4SharedMoeModel",
+    "AutoModelForCausalLM": "modeling_glm4_shared_moe.Glm4SharedMoeForCausalLM"
+}
+
+cfg_standard_moe = Glm4MoeConfig.from_pretrained(input_model)
+cfg_shared_moe = Glm4SharedMoeConfig(
+    auto_map=auto_map,
+    vocab_size=cfg_standard_moe.vocab_size,
+    hidden_size=cfg_standard_moe.hidden_size,
+    intermediate_size=cfg_standard_moe.intermediate_size,
+    num_hidden_layers=cfg_standard_moe.num_hidden_layers,
+    num_attention_heads=cfg_standard_moe.num_attention_heads,
+    num_key_value_heads=cfg_standard_moe.num_key_value_heads,
+    hidden_act=cfg_standard_moe.hidden_act,
+    max_position_embeddings=cfg_standard_moe.max_position_embeddings,
+    initializer_range=cfg_standard_moe.initializer_range,
+    rms_norm_eps=cfg_standard_moe.rms_norm_eps,
+    use_cache=cfg_standard_moe.use_cache,
+    tie_word_embeddings=cfg_standard_moe.tie_word_embeddings,
+    rope_theta=cfg_standard_moe.rope_theta,
+    rope_scaling=cfg_standard_moe.rope_scaling,
+    attention_bias=cfg_standard_moe.attention_bias,
+    attention_dropout=cfg_standard_moe.attention_dropout,
+    moe_intermediate_size=cfg_standard_moe.moe_intermediate_size,
+    num_experts_per_tok=cfg_standard_moe.num_experts_per_tok,
+    n_routed_experts=cfg_standard_moe.n_routed_experts,
+    n_shared_experts=cfg_standard_moe.n_shared_experts,
+    norm_topk_prob=cfg_standard_moe.norm_topk_prob,
+    head_dim=cfg_standard_moe.head_dim,
+    pad_token_id=cfg_standard_moe.pad_token_id,
+    eos_token_id=cfg_standard_moe.eos_token_id,
+    routed_scaling_factor=cfg_standard_moe.routed_scaling_factor,
+    first_k_dense_replace=cfg_standard_moe.first_k_dense_replace,
+    num_nextn_predict_layers=cfg_standard_moe.num_nextn_predict_layers,
+)
+
+num_experts = cfg_standard_moe.n_routed_experts
+
+with accelerate.init_empty_weights():
+    model_shared_moe = Glm4SharedMoeForCausalLM(cfg_shared_moe)
+
+model_shared_moe = model_shared_moe.to(torch.bfloat16)
+new_state_dict = {}
+pattern = f"{input_model}/model-*-of-*.safetensors"
+files = sorted(glob.glob(pattern))
+
+if len(files) == 0:
+    raise FileNotFoundError
+tensors = {}
+
+for file_path in files:
+    print(f"processing {file_path}")
+    with safe_open(file_path, framework="pt", device="cpu") as f:
+        for key in f.keys():
+            tensor = f.get_tensor(key)
+            tensors[key] = tensor
+
+for key in tensors:
+    try:
+        layer_num = int(re.search(r"\d+", key).group())
+        if layer_num >= cfg_standard_moe.num_hidden_layers:
+            continue
+    except:
+        pass
+    if "experts" not in key or "shared_experts" in key:
+        new_state_dict[key] = tensors[key]
+    elif "experts.0" in key:
+        layer_num = int(re.search(r"\d+", key).group())
+        new_state_dict[
+            f"model.layers.{layer_num}.mlp.moe_mlp.output_experts.weight"
+        ] = torch.stack(
+            [
+                tensors[f"model.layers.{layer_num}.mlp.experts.{i}.down_proj.weight"]
+                for i in range(num_experts)
+            ]
+        )
+        new_state_dict[f"model.layers.{layer_num}.mlp.moe_mlp.experts.weight"] = (
+            torch.stack(
+                [
+                    torch.cat(
+                        [
+                            tensors[
+                                f"model.layers.{layer_num}.mlp.experts.{i}.up_proj.weight"
+                            ],
+                            tensors[
+                                f"model.layers.{layer_num}.mlp.experts.{i}.gate_proj.weight"
+                            ],
+                        ],
+                        dim=0,
+                    )
+                    for i in range(num_experts)
+                ]
+            )
+        )
+model_shared_moe.load_state_dict(new_state_dict, strict=True, assign=True)
+model_shared_moe.save_pretrained(output_model_path)
+cfg_shared_moe.save_pretrained(output_model_path)
+
+
+shutil.copy(
+    "modeling_glm4_shared_moe.py",
+    output_model_path + "/" + "modeling_glm4_shared_moe.py",
+)
+shutil.copy(
+    "configuration_glm4_shared_moe.py",
+    output_model_path + "/" + "configuration_glm4_shared_moe.py",
+)
+for i in ["chat_template.jinja", "tokenizer_config.json", "tokenizer.json"]:
+    shutil.copy(input_model + "/" + i, output_model_path + "/" + i)

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45776392254b275a24e244328e0f6cbce58a31dae011c96560f7c656fcd1c2e
+size 4899547528

model-00002-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f156975edce2bebc2424265823b7206ef4d01942a5b287060b21072fff5f630
+size 4682987888

model-00003-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216f2d894bcf6c49d8fec4d23ce347c5737828a7f56c9fcce8fdd5b8f09a07e4
+size 4682987888

model-00004-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebd54e8e5b07c3a92c428d86167908e43df3238d0787d0605bbc647cfa3807d
+size 4682987888

model-00005-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800c75f575211194ceb2459d75711b2e52a5ce9c368e39e2fc6842552d5bbeec
+size 4682987888

model-00006-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0555893367e37ff2fff426272903404743574de456c20d72a6eb01bb76f9638
+size 4682987888

model-00007-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d3b02e2d94d6f706ecb171b15c7d31f0a8ca8127ebf65ce1475d1a9adae248
+size 4682987888

model-00008-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263f71ee54b5c440b7277922fb1d2366fb5c573bae182c4ab7fb0b6ac0369162
+size 4682987888

model-00009-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b825805e3185f279ee194ab2c8261abf547ed01d40971dc1758578da0e43743b
+size 4682987888

model-00010-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae61902a0b3805a5b4fbe99cc28280bdbc897d13b10549c784c8d7f5bdb9bdc3
+size 4682987912

model-00011-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ee704695042ffb44b599b327f51f3a630cbec23831ffa25003386b32990926
+size 4682987904

model-00012-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445e13c51c454d556b4390de5431f49afd128d1eed971b4ac29676bb67e15295
+size 4682987904

model-00013-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7326b4961c34c17f812e5e19ee55ab1fd694fc68f8e98819e96e862999b5d442
+size 4682987904

model-00014-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc8befb7da9721cb8528fad81e012ab89b2828fede9a283a7ed20a4332e9746
+size 4682987904

model-00015-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22015ca4df121eb8cfc5acd01354fc369fcf947f51b27652b6d04bba9cb9696b
+size 4682987904

model-00016-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780a49d1d3e54e7b37b45b9efc0d02eec3140cefe4845bbd077d2c4a71039c59
+size 4682987904

model-00017-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0be7537161cee75fbff97df03d9e585104f976b31fb73a098f8975b33b3111c
+size 4682987904

model-00018-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5528044fab3e165d495b05dfe2076fbaf06457083eecf508b28cee9b3b4ed5f1
+size 4682987904

model-00019-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f750c39a564577349c7705ec95cd4aeb73624d100df86ad95f7b8b350c2e660
+size 4682987904

model-00020-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce649f5393c57a81707a26439f82d89db5df2bb0e4ffc7b2874192e7a0735c1
+size 4682987904

model-00021-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67d951bdc8567d6e03d2ca9cd69779a96afeb090edb8e257d78fcd0ffcb33e5
+size 4682987904

model-00022-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ba8741ebe985e32c17ef26e06526223d306d73ac15f7a6600c24a22e9111ac
+size 4682987904

model-00023-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7de865761fae8c7e3c92fc7e7af3e7ba14a8846c4a97944e410181fc451d2d7
+size 4682987904

model-00024-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1f833392d772aab9f079972ace909b94e28c5c895668f153e35bb9eb100fe8
+size 4682987904

model-00025-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b734d236f3f095c50c1d1ac72dc8d02ab6a6fd1e90220663a23ea39c1ae591f
+size 4682987904

model-00026-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:282e19852b5b56b728be3aee8b8f41d516347c4f55722eefa59ac7dc270adfe2
+size 4682987904

model-00027-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca59588d218b55bb4c7cb765788c668a05f1a7acaa8eb50b1864c915b004f96
+size 4682987904

model-00028-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c33a4dce7f4bab03c1816cb0548e3dd18dafd71a990837b5e943649da04b91
+size 4682987904

model-00029-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10451b115af4d6c831155d8abce79905c06f5bd42db9551224d2260c2573c37
+size 4682987904

model-00030-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c29107055802d27415e2220abf4ac727202bc3abdf8e607c75b4603e8185c2
+size 4682987904

model-00031-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b8c0fabd37def5075c9cc4510a78f181ae12a4b15c0ea0d9b0907ca8512fce
+size 4682987904

model-00032-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec8480d163b94b1f321309a505ac1d3ea48b3f1fa86ba9ad7df0b3c9112ef36
+size 4682987904

model-00033-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8519f57ab1fbd15324f8939503c61328ae8a60940e892192ca19a927f85bb7ea
+size 4682987904

model-00034-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8076078d3ccdbdec4d375ad01e65b8c741b35e83bf772f52667b5facf492d3
+size 4682987904

model-00035-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64eca561f4471bdb4438150f7a67b147d6acdc1b028cc0b8770ea979c390136
+size 4682987904

model-00036-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79bbc64f7704ff01f30bb3b9038c5a23bb9d068a44577616db7e8854faee8dd3
+size 4682987904

model-00037-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af65b309aa1d7e7e9bec62a56dd40544b19e595eae1071510a66817ff5c2bbef
+size 4682987904

model-00038-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1607ec1d64f4b46a26770af361e5be819f919d2aab0b0f4f82fac3753f3ff0a
+size 4682987904

model-00039-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca51aec4dc1b1b456ee324edfa7f4b51c0f74fa80c6458111f6523408adb5dcc
+size 4682987904

model-00040-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcea05440633d1a87c820d1f31c95bd80b372d6937560422153a224dcc966738
+size 4682987904

model-00041-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d275875245d7c920608dba86e718c3d351a92e4a02d48973647748087e7f75
+size 4682987904

model-00042-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37547c91b22403a1044f3cfc7dc227aae89d483b8103292da9038ace6d50c539
+size 4682987904

model-00043-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a326957d379158303e37b2ea9f51db985fd0f56d3b5d5343736ad20d943bc84d
+size 4682987904

model-00044-of-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ea1d2d23665d8be7493be796b10b3fd2b9ae6193c935f8fd4f6f6489733c4e
+size 4682987904