upload mxfp4 model

.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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,46 @@
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>
+  # Tools
+  {{ tools | tojson }}<|im_end|>
+{%- endif -%}
+{%- for message in messages -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+    <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+  {%- endif -%}
+  
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {% endif %}
+
+  {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}
+    {%- if message['content'] -%}{{ message['content'] }}{%- endif -%}
+    <|tool_calls_section_begin|>
+    {%- for tool_call in message['tool_calls'] -%}
+      {%- set formatted_id = tool_call['id'] -%}
+      <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+    {%- endfor -%}
+    <|tool_calls_section_end|>
+  {%- elif message['role'] == 'tool' -%}
+    ## Return of {{ message.tool_call_id }}
+    {{ message['content'] }}
+  {%- elif message['content'] is string -%}
+    {{ message['content'] }}
+  {%- elif message['content'] is not none -%}
+    {% for content in message['content'] -%}
+      {% if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}
+        <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+      {% else -%}
+        {{ content['text'] }}
+      {%- endif -%}
+    {%- endfor -%}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+{%- endif -%}

config.json

@@ -0,0 +1,126 @@
+{
+    "_attn_implementation_autoset": false,
+    "architectures": [
+        "DeepseekV3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+        "AutoModel": "modeling_deepseek.DeepseekV3Model",
+        "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bos_token_id": 163584,
+    "dtype": "bfloat16",
+    "eos_token_id": 163586,
+    "ep_size": 1,
+    "first_k_dense_replace": 1,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 262144,
+    "model_type": "deepseek_v3",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 384,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 0,
+    "pad_token_id": 163839,
+    "pretraining_tp": 1,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "beta_fast": 1.0,
+        "beta_slow": 1.0,
+        "factor": 64.0,
+        "mscale": 1.0,
+        "mscale_all_dim": 1.0,
+        "original_max_position_embeddings": 4096,
+        "type": "yarn"
+    },
+    "rope_theta": 50000.0,
+    "routed_scaling_factor": 2.827,
+    "scoring_func": "sigmoid",
+    "seq_aux": true,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "transformers_version": "4.56.1",
+    "unsloth_fixed": true,
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840,
+    "quantization_config": {
+        "global_quant_config": {
+            "input_tensors": {
+                "dtype": "fp4",
+                "is_dynamic": true,
+                "qscheme": "per_group",
+                "ch_axis": -1,
+                "group_size": 32,
+                "symmetric": null,
+                "round_method": "half_even",
+                "scale_type": "float",
+                "scale_format": "e8m0",
+                "scale_calculation_mode": "even",
+                "mx_element_dtype": null,
+                "observer_cls": "PerBlockMXObserver",
+                "is_scale_quant": false
+            },
+            "output_tensors": null,
+            "weight": {
+                "dtype": "fp4",
+                "is_dynamic": false,
+                "qscheme": "per_group",
+                "ch_axis": -1,
+                "group_size": 32,
+                "symmetric": null,
+                "round_method": "half_even",
+                "scale_type": "float",
+                "scale_format": "e8m0",
+                "scale_calculation_mode": "even",
+                "mx_element_dtype": null,
+                "observer_cls": "PerBlockMXObserver",
+                "is_scale_quant": false
+            },
+            "bias": null,
+            "target_device": null
+        },
+        "exclude": [
+            "re:model.layers.*self_attn.*",
+            "re:model.layers.*mlp.gate",
+            "lm_head",
+            "re:model.layers.*mlp.gate_proj",
+            "re:model.layers.*mlp.up_proj",
+            "re:model.layers.*mlp.down_proj",
+            "re:model.layers.*shared_experts.*"
+        ],
+        "algo_config": null,
+        "softmax_quant_spec": null,
+        "quant_method": "quark",
+        "layer_type_quant_config": {},
+        "layer_quant_config": {},
+        "kv_cache_quant_config": {},
+        "kv_cache_post_rope": false,
+        "quant_mode": "eager_mode",
+        "version": "0.12+15553c6a61",
+        "export": {
+            "kv_cache_group": [],
+            "min_kv_scale": 0.0,
+            "pack_method": "reorder",
+            "weight_format": "real_quantized",
+            "weight_merge_groups": null
+        }
+    }
+}

configuration_deepseek.py

@@ -0,0 +1,212 @@
+# Copy from https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/configuration_deepseek.py
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+class DeepseekV3Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`DeepseekV3Model`]. It is used to instantiate an DeepSeek
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the DeepSeek-V3.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 129280):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`DeepseekV3Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 11008):
+            Dimension of the MLP representations.
+        moe_intermediate_size (`int`, *optional*, defaults to 1407):
+            Dimension of the MoE representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_nextn_predict_layers (`int`, *optional*, defaults to 1):
+            Number of nextn predict layers in the DeepSeekV3 Model.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        n_shared_experts (`int`, *optional*, defaults to None):
+            Number of shared experts, None means dense model.
+        n_routed_experts (`int`, *optional*, defaults to None):
+            Number of routed experts, None means dense model.
+        routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+            Scaling factor or routed experts.
+        topk_method (`str`, *optional*, defaults to `gready`):
+            Topk method used in routed gate.
+        n_group (`int`, *optional*, defaults to None):
+            Number of groups for routed experts.
+        topk_group (`int`, *optional*, defaults to None):
+            Number of selected groups for each token(for each token, ensuring the selected experts is only within `topk_group` groups).
+        num_experts_per_tok (`int`, *optional*, defaults to None):
+            Number of selected experts, None means dense model.
+        moe_layer_freq (`int`, *optional*, defaults to 1):
+            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
+        first_k_dense_replace (`int`, *optional*, defaults to 0):
+            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
+                                                            \--k dense layers--/
+        norm_topk_prob (`bool`, *optional*, defaults to False):
+            Whether to normalize the weights of the routed experts.
+        scoring_func (`str`, *optional*, defaults to 'softmax'):
+            Method of computing expert weights.
+        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
+            Auxiliary loss weight coefficient.
+        seq_aux = (`bool`, *optional*, defaults to True):
+            Whether to compute the auxiliary loss for each individual sample.
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
+            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
+            by meanpooling all the original heads within that group. For more details checkout [this
+            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
+            `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
+            The non-linear activation function (function or string) in the decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 2048):
+            The maximum sequence length that this model might ever be used with.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
+            The epsilon used by the rms normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            End of stream token id.
+        pretraining_tp (`int`, *optional*, defaults to 1):
+            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
+            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
+            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
+            issue](https://github.com/pytorch/pytorch/issues/76232).
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        rope_scaling (`Dict`, *optional*):
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
+            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
+            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
+            `max_position_embeddings` to the expected new maximum.
+        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+
+    ```python
+    >>> from transformers import DeepseekV3Model, DeepseekV3Config
+
+    >>> # Initializing a Deepseek-V3 style configuration
+    >>> configuration = DeepseekV3Config()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "deepseek_v3"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=129280,
+        hidden_size=7168,
+        intermediate_size=18432,
+        moe_intermediate_size = 2048,
+        num_hidden_layers=61,
+        num_nextn_predict_layers=1,
+        num_attention_heads=128,
+        num_key_value_heads=128,
+        n_shared_experts = 1,
+        n_routed_experts = 256,
+        ep_size = 1,
+        routed_scaling_factor = 2.5,
+        kv_lora_rank = 512,
+        q_lora_rank = 1536,
+        qk_rope_head_dim = 64,
+        v_head_dim = 128,
+        qk_nope_head_dim = 128,
+        topk_method = 'noaux_tc',
+        n_group = 8,
+        topk_group = 4,
+        num_experts_per_tok = 8,
+        moe_layer_freq = 1,
+        first_k_dense_replace = 3,
+        norm_topk_prob = True,
+        scoring_func = 'sigmoid',
+        aux_loss_alpha = 0.001,
+        seq_aux = True,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        initializer_range=0.02,
+        rms_norm_eps=1e-6,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=0,
+        eos_token_id=1,
+        pretraining_tp=1,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        attention_bias=False,
+        attention_dropout=0.0,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.moe_intermediate_size = moe_intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_nextn_predict_layers = num_nextn_predict_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_shared_experts = n_shared_experts
+        self.n_routed_experts = n_routed_experts
+        self.ep_size = ep_size
+        self.routed_scaling_factor = routed_scaling_factor
+        self.kv_lora_rank = kv_lora_rank
+        self.q_lora_rank = q_lora_rank
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.topk_method = topk_method
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.num_experts_per_tok = num_experts_per_tok
+        self.moe_layer_freq = moe_layer_freq
+        self.first_k_dense_replace = first_k_dense_replace
+        self.norm_topk_prob = norm_topk_prob
+        self.scoring_func = scoring_func
+        self.aux_loss_alpha = aux_loss_alpha
+        self.seq_aux = seq_aux
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.pretraining_tp = pretraining_tp
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_length": 131072,
+  "eos_token_id": 163586
+}

model-00001-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97785c9495b804480f5eb035136a7a3dccdeabe7a34af023976a72cee7afcf67
+size 995002080

model-00002-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963e36e08e711243e5e3d0288946461635f7d6d514dd241cec05788babf6711f
+size 9280353488

model-00003-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5300a977f64c22c7ceacf68a8d32942c8b42945b99c4048176d71c2c2f1ac50
+size 9280353488

model-00004-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52a59480dccd8886f86ccf4ad918d1e7212cf01f919180a4a8a32aa00dcd108
+size 9280353488

model-00005-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a506e995c8a44725f54236b6e75f3421ca9dbfd97fc82caee49349165c64c45f
+size 9280353488

model-00006-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e4eef3783e699df8a214745feb3f342fc851213a1bbba5e7e556947707774c
+size 9280353488

model-00007-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb81e2a40be415a4fd8eb586a8ac59952b17e46ddc7aaa5802f8854c08c26829
+size 9280353488

model-00008-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e785d380862075ec4b2064ca1621614496b4a5c270d97df0856a8ae2e98883
+size 9280353488

model-00009-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ab0033fb20262518f7323dee65918398d8805199a31e2b29cf19df58d0cb04
+size 9280353488

model-00010-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace527c71fcd37b085cba3e44de8e3f6727c9d0f42b41dcb12bb0863eb7cafc2
+size 9280353488

model-00011-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0569facf80d944f7715aeb2b8a105c29a680349b7d1ba3d67f4edbd117e9316d
+size 9280355808

model-00012-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f19b7cc95a2e9f24e89d620ccba924832fd68fa72e921648f0c860bda742b8
+size 9280355808

model-00013-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8d84793a00e9e29d55b59183ead1d7b8d0d52affc0331dcac51a4ec922c8fe
+size 9280355808

model-00014-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef1fee0f6f31ec4392c445c5ac8569374f4ed42c1b739011174d831e4028cfd
+size 9280355808

model-00015-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd80e24b60865a2b9134a85604f6852c951cf7658e8e2be015de7d42a6585aa6
+size 9280355808

model-00016-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e55abb6cf8399be5c31e5bc4718c8a06dfcfa840f7ccb6faa9d27c20aacd98
+size 9280355808

model-00017-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e5fb01edb2ba9f136db01dae2811b59b69372979fdcb55749ee8037b24e7a8
+size 9280355808

model-00018-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c47a9d10e9cf4e65688d0ba75cbd2a8ab59e9e3e54637edd4a0515a7fe622d3
+size 9280355808

model-00019-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6be632fa6059062ab5d3afbc0a9afa8b57f7b633e39543a9ad8df78f41af51e
+size 9280355808

model-00020-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a1f3d892281252d82c52f7c5a3e2500aa11332500229bc559f29e578f35a12
+size 9280355808

model-00021-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698704cef5152a4af86721b9c24103ae857f0506542186416adf0a8bb3ba3349
+size 9280355808

model-00022-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b5a470e2432e4c6c581c6bd1b72460ee24bd627092233382a779e9bcf50399
+size 9280355808

model-00023-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0bb40a80d5eba3cd5db1e7e96d2fa506cd3fe36f9437838e759ea2a0765001
+size 9280355808

model-00024-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617d6b4946f9e1fc4a6ae32efc53fbb9f562dd49dbfbd6a9c855a7a68d477038
+size 9280355808

model-00025-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86dce5b6fc028d000f5908c2ab5180b23011a5836de280c3322c337cce6dca18
+size 9280355808

model-00026-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70a71fc3ca1659fbdcedfdc956c0a5b25c409335b1846db2534c2218be1865c
+size 9280355808

model-00027-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e623d550e6f77651868902f6868e9e0f6bc5e51b9e12c12f51ed91dbd36e832c
+size 9280355808

model-00028-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0f8d11cfa1afe2f40ff11a9e9a9ad90b0a9db4180ea18735905d5cd77c87d7
+size 9280355808

model-00029-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703d5fe54d24099e60be172136d4eba5f43ffeb6a62dbfc4a55052e1913a38e6
+size 9280355808

model-00030-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4041b382ec48ff3c0631aff5dc7ecca0b0e2aace81d2c6812a918f5bb2c9e91e
+size 9280355808

model-00031-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb3a53aa7a160cf1395549c4b96d9ff86a073fe3222d5be4117b64fd954b370
+size 9280355808

model-00032-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8299a78346022989d95258343d7b7ca505fa89cf0c095ce625dbec8b604a1c8
+size 9280355808

model-00033-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a180ad15eb8ad7010ac877cef865de956e9cc7a979e590042d9a4c89f2dbbfd7
+size 9280355808

model-00034-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54d0760643f2f09fef77f82f169cb232c502e404578edac2079635139fbcc4e
+size 9280355808

model-00035-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22723f6510c57561e1b436a0d2b92bde5a68ccb696e1ca98aadd470f776d153
+size 9280355808

model-00036-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4f4bccdcd7e35a0e1cee41e78961a34c59d5fefa9acd2a0182d862e34d3d93
+size 9280355808

model-00037-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e188c3bcb37dee2b61e5727315bab70f43d879283d26a9a36bb3fdd5837887a
+size 9280355808

model-00038-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c51bafa930721e047ba34bc6506b497c250e9ec5100bd9c863fe0c7ad82fe71
+size 9280355808

model-00039-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd31abf5e5ecbe23e471570f3abebf0d8870a3662b6c595a50ec27da6f20405d
+size 9280355808

model-00040-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7edf9873cd645394a0ecb00a6b4486878f82bcc50efa7d6c0b5a71074417a2dd
+size 9280355808

model-00041-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fa1d782af5be52c5546fccc50425b14846e56a68a42ecb3e8aed53e3ee336b
+size 9280355808

model-00042-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7f8a0614de1591a39fbe795b387f487de097956fc8e421e86f9e844f42d70c
+size 9280355808

model-00043-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9433105359d6799aa0c43c3be5d95605e829892ef9cc64b1cd7e0b3df9281a54
+size 9280355808

model-00044-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b381669a23a70c3e39afc87cc83586962b6a7cb671e3841a780f0397f0cfe457
+size 9280355808

model-00045-of-000062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f3176abb91022659845dad62351afcaa9c850fe6d68413a51efc3490b6ff1a
+size 9280355808