new model

chat_template.jinja

@@ -0,0 +1,101 @@
+{%- if not add_generation_prompt is defined %}
+    {%- set add_generation_prompt = false %}
+{%- endif %}
+{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {%- set ns.system_prompt = ns.system_prompt + message['content'] %}
+            {%- set ns.is_first_sp = false %}
+        {%- else %}
+            {%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
+{%- if tools is defined and tools is not none %}
+    {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
+    {%- for tool in tools %}
+        {%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
+    {%- endfor %}
+    {%- if ns.system_prompt|length != 0 %}
+        {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
+    {%- else %}
+        {%- set ns.system_prompt = tool_ns.text %}
+    {%- endif %}
+{%- endif %}
+{{- bos_token }}
+{{- ns.system_prompt }}
+{%- set last_index = (messages|length - 1) %}
+{%- for message in messages %}
+    {%- set content = message['content'] %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_first = false -%}
+        {%- set ns.is_last_user = true -%}
+        {%- if loop.index0 == last_index %}
+            {{- '<｜User｜>' + content }}
+        {%- else %}
+            {{- '<｜User｜>' + content + '<｜Assistant｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {%- if '</think>' in content %}
+            {%- set content = (content.split('</think>')|last) %}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>'}}
+        {%- endif %}
+        {%- set ns.is_first = false %}
+        {%- set ns.is_tool = false -%}
+        {%- set ns.is_output_first = true %}
+        {%- for tool in message['tool_calls'] %}
+            {%- set arguments = tool['function']['arguments'] %}
+            {%- if arguments is not string %}
+                {%- set arguments = arguments|tojson %}
+            {%- endif %}
+            {%- if not ns.is_first %}
+                {%- if content is none %}
+                    {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                }
+                {%- else %}
+                    {{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+                {%- endif %}
+                {%- set ns.is_first = true -%}
+            {%- else %}
+                {{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
+            {%- endif %}
+        {%- endfor %}
+        {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
+        {%- set ns.is_last_user = false -%}
+        {%- if ns.is_tool %}
+            {{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
+            {%- set ns.is_tool = false -%}
+        {%- else %}
+            {{- content + '<｜end▁of▁sentence｜>'}}
+        {%- endif %}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false -%}
+        {%- set ns.is_tool = true -%}
+        {%- if ns.is_output_first %}
+            {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+            {%- set ns.is_output_first = false %}
+        {%- else %}
+            {{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+{%- if ns.is_tool %}
+    {{- '<｜tool▁outputs▁end｜>'}}
+{%- endif %}
+{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
+{%- if add_generation_prompt and not ns.is_tool %}
+    {{- '<｜Assistant｜>'}}
+{%- endif %}

config.json

@@ -0,0 +1,190 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 18432,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 128,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 2,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "model.layers.61.embed_tokens",
+      "model.layers.61.eh_proj",
+      "model.layers.61.shared_head.head",
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": true,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      }
+    },
+    "kv_cache_post_rope": false,
+    "kv_cache_quant_config": {},
+    "layer_quant_config": {
+      "*self_attn*": {
+        "bias": null,
+        "input_tensors": {
+          "ch_axis": 1,
+          "dtype": "fp8_e4m3",
+          "group_size": null,
+          "is_dynamic": true,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerChannelMinMaxObserver",
+          "qscheme": "per_channel",
+          "round_method": "half_even",
+          "scale_calculation_mode": null,
+          "scale_format": null,
+          "scale_type": "float",
+          "symmetric": true
+        },
+        "output_tensors": null,
+        "target_device": null,
+        "weight": {
+          "ch_axis": 0,
+          "dtype": "fp8_e4m3",
+          "group_size": null,
+          "is_dynamic": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerChannelMinMaxObserver",
+          "qscheme": "per_channel",
+          "round_method": "half_even",
+          "scale_calculation_mode": null,
+          "scale_format": null,
+          "scale_type": "float",
+          "symmetric": true
+        }
+      },
+      "model.layers.61.*": {
+        "bias": null,
+        "input_tensors": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": true,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        },
+        "output_tensors": null,
+        "target_device": null,
+        "weight": {
+          "ch_axis": -1,
+          "dtype": "fp4",
+          "group_size": 32,
+          "is_dynamic": false,
+          "is_scale_quant": false,
+          "mx_element_dtype": null,
+          "observer_cls": "PerBlockMXObserver",
+          "qscheme": "per_group",
+          "round_method": "half_even",
+          "scale_calculation_mode": "even",
+          "scale_format": "e8m0",
+          "scale_type": "float",
+          "symmetric": null
+        }
+      }
+    },
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null,
+    "version": "0.11.1"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.57.6",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

configuration_deepseek.py

@@ -0,0 +1,199 @@
+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.
+        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',
+        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,
+        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
+        # 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.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 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9d00e11f82c9af55b9aafbc69c7d10cd62347fdac9b3c3731e06bec2783b56
+size 4996706336

model-00002-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d00e6582e2a34f1cd723f2a353d4b4692cec4207505a4cd23028181de9c5ee2
+size 4995148712

model-00003-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e928b85055c236d9a965ecca91457e736371e0e8490cd063019a7119c03da4d6
+size 4999180664

model-00004-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218e63e69a4251a0d92c55bcf59fff5d41a3c76f3650cf840f70ea5935b61c39
+size 4995148408

model-00005-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a63e063c9cb18dc5c25058a34b38c6c0be1dee62659c99f70a6eb7e63994d7
+size 4995148408

model-00006-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816c007eff1d3d89631c7a5bd4beadfa8798175de1ca356f836508375ce279c9
+size 4995148512

model-00007-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7328160f3b04c2c3aacdad732fc2d592dfa6f64a3538481e17fe2439a1a2a5c4
+size 4995148712

model-00008-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d07fa36c26334c6b868d29c2de483e3f0765e88792fae2705ef1eca63906864
+size 4999180704

model-00009-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7f505e1e91a348dc2108e5424bd6031af79edda4a9b39814494d55d8b9fc4e
+size 4995148408

model-00010-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9beb352a38b502785f70cead261072e98888e8db3ad6a0a5370c1d7512c027d2
+size 4995149240

model-00011-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b969695d04d6748cf4433381c8b25f6508a2869a4e2695602a6dac55d4b149
+size 4995149720

model-00012-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8cad884efb28032c5d29234bd02ac5d540004512334d367baa58dfb9e3fad5
+size 4995149960

model-00013-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb90a0ddfd3dbca6e869b064328e5eed0800833fb17c5814ffa53255342d4f0e
+size 4999182032

model-00014-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bef1943634b6c3bf469f30b94e66de181d3d71acb9a1ae93b32280373ce4eba
+size 4995149656

model-00015-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c93f28a46dbbbe2202a8b40328b14a6efd4fc580fcf30ea5fa8fac5edaf977
+size 4995149656

model-00016-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07ed315d2fb14b58b7fed2b3fdeb1f378cd3dfcdf4ead73d2413124b88b0fe8
+size 4995149680

model-00017-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dc28429c32b7fc4d51d1ef9b1965161b9f49a6cf79cf0cbe0433c4419e14d7
+size 4995149960

model-00018-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7296182d799b02fa3e0b934e95b80c70fedf065ecfbb7b0217149363af150d31
+size 4982702128

model-00019-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c088fe230215e9af12e543cbf995d111bcbb4a512c22c2b18d2a94f7c2fc1b5a
+size 4996031512

model-00020-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfc719da337507abb63f9e853ff4a3a40dc32cf69f902d630a43e2277337c5a
+size 4995149656

model-00021-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254fb0da68fe75dc020d560430cd77481f9e2185cf733dce040eb72c39acd3b2
+size 4995149656

model-00022-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a326b8394726596a02ef2b802dd76d74cb21f9db11f4f8be45e436fe7aa4c3
+size 4995149952

model-00023-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61d24c35e5c382bcaac0bf7a6bed4974ca2019670632992efa77dffed5b31a6
+size 4893292936

model-00024-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd33df5112e203e25538db2b3e9bf4bccb5b43666940220eed09a1c7e53bf00
+size 4999651368

model-00025-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a25995623d6e5b95f10dbeac5e83e20979b6d77beb94abbc5f6424ebcd9f38dc
+size 4995149656

model-00026-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15481f628b2cca43326730382b81d814729835507d96100e012ce7ea04721bb
+size 4995149656

model-00027-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb682794cc86517d9d9aab3724524390d0066134395cd11b2e4b2c4777c9b86
+size 4995149928

model-00028-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce442ac12fc7f63496b478194d59df1807a700e338b059a1243bcae95760b5bf
+size 4995150016

model-00029-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22166c0b3afdc8a2db7f4f6b8ae3bedd7232ab8d4a17177be124dbbebc86c59
+size 4999181768

model-00030-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2762b79056f5015d444a5a68f7fde5834a62f3448aba96e8e476faf8e0a256af
+size 4995149656

model-00031-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c97e970066da2eb362af7efc4b0029a51e9aaaac36f8a5abe249690d77dd7e1
+size 4995149656

model-00032-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef15a42f8ac0de94eee7bf5e9fdd4b26c867e412ecb0cbdb482d03452614141
+size 4995149888

model-00033-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7894349584003816b0e7cf54e14236155b8916e1864db9593f6c403384b89df0
+size 4995149968

model-00034-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d16712836abc0279b596b717e5518bd0afc04c201921581c7b8f678712707f
+size 4999181848

model-00035-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fd60795780100286b6274b79d069ab32d09eda1bb498daf43619250f2e39a7
+size 4995149656

model-00036-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb20289f7a816596129a5b245d094b4b9abbb091451baab213e2a0cb7899e751
+size 4995149656

model-00037-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acf2caae26d79c6bf3db918fc3693f2bc43f9c630310fccf09025d290f81c99
+size 4995149848

model-00038-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823d0c3e77509be96aee69be98c4fdf3978122c16fd39bc10e4bf6859de9f72f
+size 4995149968

model-00039-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610c554c62767a25f5904f41f11e77011b062e2be6bda35186f782fc8ae8b62c
+size 4999181896

model-00040-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0e91565a4210c920931943a5eed51d56e8022e7e80728ce48ae4813aed6844
+size 4995149656

model-00041-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1339f3d8e1a422d20faf4b07fa40e12d3eee36e5e8f3dc08397216b1250f722
+size 4995149656

model-00042-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1ce69017f8d1ba7cbf6fd88b957c1489780ac64ab9a60f3ecc4b142aefef57
+size 4995149808

model-00043-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1958af77c7a1b0312cfb85badeec2488b7b90cc9ebd0fe3664ede510120c5085
+size 4995149968

model-00044-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112d167a780a79744aa050e6fde08717c95b5bc177bcc70b14331ebaaa6fad26
+size 4999181936

model-00045-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0002b376e180bb2079d41f43d2d63aa5604827be791f185277ddea472ae27fe5
+size 4995149656

model-00046-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6708e902f55277959d6d18e35a5b1ea9f85b97b81977c4f513513fac3afc60b6
+size 4995149656