Add files using upload-large-folder tool

README.md

@@ -0,0 +1,17 @@
+---
+license: mit
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- transformers
+- mlx
+base_model: meituan-longcat/LongCat-Flash-Chat
+---
+
+This model [finding1/LongCat-Flash-Chat-MLX-5.5bpw](https://huggingface.co/finding1/LongCat-Flash-Chat-MLX-5.5bpw) was
+converted to MLX format from [meituan-longcat/LongCat-Flash-Chat](https://huggingface.co/meituan-longcat/LongCat-Flash-Chat)
+using mlx-lm version **0.27.1** by running
+`mlx_lm.convert --quantize --q-bits 5 --mlx-path MLX-8.5bpw --hf-path meituan-longcat/LongCat-Flash-Chat`
+until it crashed with a `KeyError`;
+[adding `"model_type": "longcat_flash",` to the downloaded `config.json`](https://github.com/ml-explore/mlx-lm/issues/433#issuecomment-3262138687),
+then running the command again.

chat_template.jinja

@@ -0,0 +1,138 @@
+{%- set tool_choice = tool_choice | default('auto') %}
+{%- set ns = namespace(rounds = 0, tool_types = [], last_query_index = -1) %}
+
+{%- if tools and tool_choice != 'none' %}
+    {{- "# Tools
+" }}
+    {{- "You have access to the following tools: 
+
+" }}
+    {%- for tool in tools %}
+        {%- if tool.type in ['code_interpreter', 'function'] %}
+            {%- if tool.type not in ns.tool_types %}
+                {%- set ns.tool_types = ns.tool_types + [tool.type] %}
+                {{- "## Tool namespace: " ~ tool.type ~ "
+
+" }}
+            {%- endif %}
+            {%- if tool.type == 'code_interpreter' %}
+                {%- set tool = {"type":"code_interpreter","function":{"name":"code_interpreter_preview","description":"The code will be executed in a stateful Jupyter notebook sandbox environment, only supports local computation, data processing, and file operations. 
+Code sandbox environment (network isolated) Any external network requests or online API calls are prohibited. 
+If online functionality is needed, please use other permitted tools. 
+Code will respond with the output of the execution or time out after 60.0 seconds. ","parameters":{"type":"object","properties":{"language":{"type":"string","description":"The programming language of the code to be executed. Available values: python (Default), java, go, js, ts, c, c++."},"code":{"type":"string","description":"Python code to be executed must not include the following:
+- Importing network libraries such as requests, httplib, etc.
+- Any form of HTTP requests.
+- External API calls.
+- Network port operations. Example: ```python
+import pandas as pd
+pd.DataFrame({'A':[1,2]})
+```"},"timeout":{"type":"number","description":"The maximum execution time of the code, in seconds. Default is 60.0."}}},"required":["code"]}} %}
+            {%- endif %}
+            {{- "### Tool name: " + tool.function.name + "
+
+" }}
+            {{- "Description: " + tool.function.description + "
+
+" }}
+            {{- "InputSchema: 
+" + tool.function.parameters | tojson(indent=2) + "
+
+" }}
+        {%- endif %}
+    {%- endfor %}
+    {{- '**Note**: For each function call, return a json object with function name and arguments within <longcat_tool_call></longcat_tool_call> XML tags as follows:
+<longcat_tool_call>
+{"name": <function-name>, "arguments": <args-dict>}
+</longcat_tool_call>
+' }}
+    {{- 'When multiple functions need to be called simultaneously, each function call should be wrapped in its own <longcat_tool_call> tag and placed consecutively. For example:
+<longcat_tool_call>
+{"name": <function-name>, "arguments": <args-dict>}
+</longcat_tool_call><longcat_tool_call>
+{"name": <function-name>, "arguments": <args-dict>}
+</longcat_tool_call>
+
+' }}
+    {{- "# Messages
+" }}
+
+    {%- for idx in range(messages|length - 1) %}
+        {%- set msg = messages[idx] %}
+        {%- if msg.role == 'assistant' and not msg.tool_calls %}
+            {%- set ns.last_query_index = idx %}
+        {%- endif %}
+    {%- endfor%}
+{%- endif %}
+
+{%- for msg in messages %}
+    {%- if msg.role == "system" %}
+        {{- "SYSTEM:" + msg.content }}
+    {%- elif msg.role == "user" %}
+        {%- if loop.first %}
+            {{- "[Round " ~ (ns.rounds) ~ "] USER:" }}
+        {%- else %}
+            {{- " [Round " ~ (ns.rounds) ~ "] USER:"}}
+        {%- endif %}
+        {%- set ns.rounds = ns.rounds + 1 %}
+        {%- if msg["files"] %}
+            {{- '<longcat_files>
+' ~ msg.files | tojson(indent=2) ~ '
+</longcat_files>' }}
+        {%- endif %}
+        {{- msg.content }}
+    {%- elif msg.role == "assistant" %}
+        {{- " ASSISTANT:" }}
+        {%- if enable_thinking == true and msg.reasoning_content and ns.tool_types != [] and loop.index0 > ns.last_query_index %}
+            {{- "
+<longcat_think>
+" ~ msg.reasoning_content ~ "
+</longcat_think>
+" }}
+        {%- endif %}
+        {%- if msg.content%}
+            {{- msg.content }}
+        {%- endif %}
+        {%- if msg.tool_calls %}
+            {%- for tool_call in msg.tool_calls -%}
+                {{- "<longcat_tool_call>
+" -}}
+                {%- if tool_call.function.arguments is string -%}
+                    {"name": "{{ tool_call.function.name}}", "arguments": {{tool_call.function.arguments}}}
+                {%- else -%}
+                    {"name": "{{ tool_call.function.name}}", "arguments": {{tool_call.function.arguments | tojson}}}
+                {%- endif -%}
+                {{- "
+</longcat_tool_call>" }}
+            {%- endfor %}
+        {%- endif %}
+        {{- "</longcat_s>" -}}
+    {%- elif msg.role == "tool" %}
+        {{- " TOOL:" -}}
+        {%- if msg.name -%}
+            {"name": {{msg.name | tojson}}, "content": {{msg.content | tojson}}}
+        {%- else -%}
+            {"content": {{msg.content | tojson}}}
+        {%- endif -%}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %} 
+    {%- if enable_thinking == true %}
+        {{- " /think_on" }}
+        {%- if thinking_budget %}
+            {%- if thinking_budget < 1024 %}
+                {%- set thinking_budget = 1024 %}
+            {%- endif%}
+            {{- "
+thinking_budget: < " ~ thinking_budget ~ "."}}
+        {%- endif %}
+        {{- " ASSISTANT:<longcat_think>
+"}}
+    {%- elif enable_thinking == false %}
+        {{- " /think_off ASSISTANT:<longcat_think>
+
+</longcat_think>
+" }}
+    {%- else %}
+        {{- " ASSISTANT:" }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,272 @@
+{
+    "architectures": [
+        "LongcatFlashForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_method": "MLA",
+    "auto_map": {
+        "AutoConfig": "configuration_longcat_flash.LongcatFlashConfig",
+        "AutoModel": "modeling_longcat_flash.LongcatFlashModel",
+        "AutoModelForCausalLM": "modeling_longcat_flash.LongcatFlashForCausalLM"
+    },
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "expert_ffn_hidden_size": 2048,
+    "ffn_hidden_size": 12288,
+    "hidden_size": 6144,
+    "kv_lora_rank": 512,
+    "max_position_embeddings": 131072,
+    "mla_scale_kv_lora": true,
+    "mla_scale_q_lora": true,
+    "model_type": "longcat_flash",
+    "moe_topk": 12,
+    "n_routed_experts": 512,
+    "num_attention_heads": 64,
+    "num_layers": 28,
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine",
+        "model.layers.0.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 5,
+        "mode": "affine",
+        "model.layers.0.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.router.classifier": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000000.0,
+    "routed_scaling_factor": 6.0,
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 131072,
+    "zero_expert_num": 256,
+    "zero_expert_type": "identity"
+}

configuration_longcat_flash.py

@@ -0,0 +1,216 @@
+
+"""LongcatFlash model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.modeling_rope_utils import rope_config_validation
+
+
+LONGCAT_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
+
+
+class LongcatFlashConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`LongcatFlashModel`]. It is used to instantiate an LongcatFlash
+    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 LongcatFlash.
+    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 131072):
+            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`LongcatFlashModel`]
+        hidden_size (`int`, *optional*, defaults to 7168):
+            Dimension of the hidden representations.
+        ffn_hidden_size (`int`, *optional*, defaults to 18432):
+            Dimension of the MLP representations.
+        expert_ffn_hidden_size (`int`, *optional*, defaults to 2048):
+            Dimension of the MoE representations.
+        num_layers (`int`, *optional*, defaults to 61):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 128):
+            Number of attention heads for each attention layer in the Transformer decoder.
+        num_key_value_heads (`int`, *optional*, defaults to 128):
+            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`.
+        n_routed_experts (`int`, *optional*, defaults to 256):
+            Number of routed experts.
+        routed_scaling_factor (`float`, *optional*, defaults to 2.5):
+            Scaling factor or routed experts.
+        kv_lora_rank (`int`, *optional*, defaults to 512):
+            Rank of the LoRA matrices for key and value projections.
+        q_lora_rank (`int`, *optional*, defaults to 1536):
+            Rank of the LoRA matrices for query projections.
+        qk_rope_head_dim (`int`, *optional*, defaults to 64):
+            Dimension of the query/key heads that use rotary position embeddings.
+        v_head_dim (`int`, *optional*, defaults to 128):
+            Dimension of the value heads.
+        qk_nope_head_dim (`int`, *optional*, defaults to 128):
+            Dimension of the query/key heads that don't use rotary position embeddings.
+        norm_topk_prob (`bool`, *optional*, defaults to `True`):
+            Whether to normalize the weights of the routed experts.
+        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 4096):
+            The maximum sequence length that this model might ever be used with.
+        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 0):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 1):
+            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.
+        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.
+        attention_method (`str`, *optional*, defaults to `"MLA"`):
+            The attention method to use.
+        initializer_range (`float`, *optional*, defaults to 0.006):
+            The initializer range for the model.
+        router_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in the router.
+        zero_expert_num (`int`, *optional*, defaults to `None`):
+            The number of zero experts to use.
+        zero_expert_type (`str`, *optional*, defaults to `None`):
+            The type of zero expert to use.
+
+    ```python
+    >>> from transformers import LongcatFlashModel, LongcatFlashConfig
+
+    >>> # Initializing a LongcatFlash style configuration
+    >>> configuration = LongcatFlashConfig()
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "longcat_flash"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    base_model_tp_plan = {
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.mlp.experts.*.gate_proj": "local_colwise",
+        "layers.*.mlp.experts.*.up_proj": "local_colwise",
+        "layers.*.mlp.experts.*.down_proj": "local_rowwise",
+        "layers.*.mlps.*.gate_proj": "local_colwise",
+        "layers.*.mlps.*.up_proj": "local_colwise",
+        "layers.*.mlps.*.down_proj": "local_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=131072,
+        hidden_size=7168,
+        ffn_hidden_size=18432,
+        expert_ffn_hidden_size=2048,
+        num_layers=61,
+        num_attention_heads=128,
+        num_key_value_heads=None,
+        n_routed_experts=256,
+        routed_scaling_factor=1,
+        kv_lora_rank=512,
+        q_lora_rank=1536,
+        qk_rope_head_dim=64,
+        v_head_dim=128,
+        qk_nope_head_dim=128,
+        mla_scale_q_lora=True,
+        mla_scale_kv_lora=True,
+        moe_topk=8,
+        norm_topk_prob=False,
+        hidden_act="silu",
+        max_position_embeddings=4096,
+        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,
+        attention_bias=False,
+        attention_dropout=0.0,
+        attention_method='MLA',
+        initializer_range=0.006,
+        router_bias=False,
+        zero_expert_num=None,
+        zero_expert_type=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.ffn_hidden_size = ffn_hidden_size
+        self.expert_ffn_hidden_size = expert_ffn_hidden_size
+        self.num_layers = num_layers
+        self.num_attention_heads = num_attention_heads
+        self.n_routed_experts = n_routed_experts
+        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.qk_head_dim = qk_nope_head_dim + qk_rope_head_dim
+        self.moe_topk = moe_topk
+        self.norm_topk_prob = norm_topk_prob
+        self.mla_scale_q_lora = mla_scale_q_lora
+        self.mla_scale_kv_lora = mla_scale_kv_lora
+        self.attention_method = attention_method
+        self.initializer_range = initializer_range
+        self.router_bias = router_bias
+        self.zero_expert_num = zero_expert_num
+        self.zero_expert_type = zero_expert_type
+
+        if self.attention_method == "MLA":
+            self.head_dim = qk_rope_head_dim
+        else:
+            ValueError('attention_method should be one of ["MLA"]')
+
+
+        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.rms_norm_eps = rms_norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+
+        rope_config_validation(self)
+
+        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,
+        )
+
+    @property
+    def num_hidden_layers(self):
+        return self.num_layers
+
+
+__all__ = ["LongcatFlashConfig"]

generation_config.json

@@ -0,0 +1,7 @@
+{
+    "_from_model_config": true,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "pad_token_id": 3,
+    "transformers_version": "4.55.0"
+}

model-00001-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:686da8791145ba82cb3e60158eda0f690cb88d7fcc2dd571d5e614baf17e1bc0
+size 4982833873

model-00002-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972b4be672b881f5172fa546dfbf36dd748228888e146774bfd5e4f89213f633
+size 4429185427

model-00003-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4671be71cb1afbddaa40abe8eb34ed78f80816fc2620445f8939eff017f48cfe
+size 4870523118

model-00004-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed2285e92b5bda5c005dfa4a5cc8f65d34867852989e3048604c9b43996d78e
+size 4429185433

model-00005-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add36338563d089251d50f1debf0880d0b702d9451e0ead759158a01614efe61
+size 4429185427

model-00006-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb02edd015ead840e64255daf096887116cb73b711f3cc1ba29d2f39ffaa559
+size 4870523134

model-00007-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa6aaa8e7613d8860a9cf4025fe5bb70493236bad32fe3c23b75872ec9a5f5a
+size 4429185433

model-00008-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e63529f96436a06245bb7850ec63fb6104fd6049767df9228a7dc399866bb8a
+size 4429185427

model-00009-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afb85377f3d76804626b0afa56f4c4910c05a617ab609f78f45c10632bb9219
+size 4870523102

model-00010-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56408f987c0bab3108f71660c550e2135895c67860e0e9ed012f323f71c8f979
+size 4429185433

model-00011-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7aaf63fab521c746fa00623592c8d6ee2f3f2e27b9b85be11d2f462a8ea979
+size 4429185427

model-00012-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d8f063f7926575f539fe41fffa51d78bee8383d0e326da13f0262b3627782f
+size 4870523134

model-00013-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16514ae49100746e4a2d6d282c323d2068a74d74bfa3e061744f7068f212f2d7
+size 4429185433

model-00014-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1dbe5dd3e816ad853ef42209e70c93446ebcc8df433e5e3512d48ef4c1b442
+size 4429185427

model-00015-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5def97c2a8dfd370c3fd4ee8810be7d1cc23b13917915c208b548e4c0da44d9a
+size 4870523124

model-00016-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78e5b9fa0addaa036a181108f924a2ff2d1c21e3d3736c0575fc4ee92ae8611
+size 4429185433

model-00017-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8d72dec11b4883213088d13742dd4951f726a4adb92138492d9122be1bb085
+size 4429185427

model-00018-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4319a2152a8adb68f3423b4a472554069ca50eeda40cd1bc97e4055598899741
+size 4870523122

model-00019-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28382f1e42a534dbc208f243374211973293b58d4275e9b6f0bae0c6003dfea3
+size 4429185433

model-00020-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5c87022a8e4a6b76f66d18525c7ca120691e3f232e57bd27197fbb7c895626
+size 4429185427

model-00021-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8fcbcbdf91a193309655c664b9b8133ee6bc0a7c95daa0b35ff9ef3e71c630
+size 4870523160

model-00022-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42078c61b5d2171b80c371a3c0121b2f4289185225081a8de20644a9593bc86a
+size 4429185433

model-00023-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213d1db8a10013b778880d572da09d84f999304d5ce7d7eb6e4ca7e978ab3fc6
+size 4429185427

model-00024-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65ea40b028ef8dab8e7e6fba7a638c4c2ba2c6bcd93286d505dfcd96d58aeda
+size 4870523130

model-00025-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1e71f00377512009fc340f9d9c0410eef34625cc4f0fb1d8d39af995c65301
+size 4429185433

model-00026-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7e1f46560f71bdb3472120dd69f577bbcba3c457e44005c2293c1e7605a5ad
+size 4429185427

model-00027-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e90b71a80bf35ad2e55d3e1b3441a2a20751b3613bae67554356592cc20acd8
+size 4870523106

model-00028-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce1381073be1b372b231572527eb4f2fe294b9b97b482797d3a566eb5f76f54
+size 4429185433

model-00029-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50deb062d16565873202cfb8a0d6a1f819ef8b61d402e16e5d4133acc8e93034
+size 4429185427

model-00030-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce970ed66c8b85af1e1eeba1c1f2145e453b237901f2ab8626aaa241c0148a3f
+size 4870523128

model-00031-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0451132a1783b096076dc8ba51b3e06d18fd9b217842de3e5c5647c11ff0d93b
+size 4429185436

model-00032-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa31062615ef88d7532f3a7342c818946aa26a8c567158c34601dce00dee8c87
+size 4429185430

model-00033-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b97362bd0cde8d3208bdd2e622d26eb0deb3ffce4582d3d1bac7b88cbdbb06
+size 4870523265

model-00034-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed91549e70382475f6c1038b6a08e492d6a8c0cae2d64a8aa94af3843390fd3
+size 4429185436

model-00035-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b21a96df69482c02a42d0a9e632c7cc80d65484d468df8ba37b702c21f434d
+size 4429185430

model-00036-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db282c7c4d5cf4bd5f76bbd45a462118f7977f380cb941a79f63be6d35c6676c
+size 4870523213

model-00037-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e068b3108d11849ab41883beac8b9a5e069648f127975c91809e26da4d3f0bdc
+size 4429185436

model-00038-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5cf2b9f2642ea63a3ad2531850628f35e98506ee9e6bee489ccf204d6936ce
+size 4429185430

model-00039-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c906905d4337f30f7a6b6d8c82e33369045369a184cda01db2197fdfc9d4347
+size 4870523163

model-00040-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6616f0a433580f12e85f6c24023077b515a6a076b6498060a6073a4e30d7c7f9
+size 4429185436

model-00041-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbf5620fb091176a7e0c05d76ca82740a5ceb6b11186a7d0773d0c93dd6a9df
+size 4429185430

model-00042-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566ff1861cfad6832b702774d381965b3c70d4cdc5554a077085ce10454ede9e
+size 4870523155

model-00043-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e723c92d28145254f3e964be6a60f25fa8eb497e9a02531252c757b3f6fb0a1a
+size 4429185436

model-00044-of-00085.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58fcf48f43ed595d16c0cb932f1c129bed18e2a8bbe3ba9b7e6f72313db8852e
+size 4429185430