Upload MLX converted model with quantization settings

README.md

@@ -0,0 +1,46 @@
+---
+base_model: unsloth/DeepSeek-R1-0528-BF16
+language:
+- en
+library_name: transformers
+license: mit
+tags:
+- deepseek
+- unsloth
+- transformers
+- mlx
+- mlx-my-repo
+---
+
+# cs2764/DeepSeek-R1-0528-BF16-mlx-mixed_4_6
+
+The Model [cs2764/DeepSeek-R1-0528-BF16-mlx-mixed_4_6](https://huggingface.co/cs2764/DeepSeek-R1-0528-BF16-mlx-mixed_4_6) was converted to MLX format from [unsloth/DeepSeek-R1-0528-BF16](https://huggingface.co/unsloth/DeepSeek-R1-0528-BF16) using mlx-lm version **0.27.1**.
+
+## Quantization Details
+
+This model was converted with the following quantization settings:
+
+- **Quantization Strategy**: mixed_4_6 (Mixed precision)
+- **Average bits per weight**: 4.809
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("cs2764/DeepSeek-R1-0528-BF16-mlx-mixed_4_6")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

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 %}

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,
+  "eos_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bae7785faff93edf0d21d3f32e73626680343ed5b6572edc623c49587257be1
+size 3824238773

model-00002-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7c651f7cdb6221d67b0d014b56e4e1f08c1604f74b1ab9246e46658b8b3b26
+size 5304780030

model-00003-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a879e181ab2dd26f3e218fa57c82aa3dfa74140060ad243057b81cb10ad89c57
+size 4227859222

model-00004-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966895a23939e80749a469ce8e80cac18221f867dc27457bf37eb6c5caacdd4f
+size 5304780100

model-00005-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64b602671174a6ec21735bd434a608b2ed54962aff10363c76455982bff7bda
+size 5304780038

model-00006-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8302b217eeda0a9ab261090fa419499efa37034a703885264a0324ff2bc275a0
+size 4227859218

model-00007-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bcb327d66fe6cddac9faaa7410825bd950bfb15496e185334901c2395873fb
+size 5304780098

model-00008-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cca8ec32c6ccb6d47d6c47132a9c58772069678a542e7c58da3613c4b7a40a
+size 4361585894

model-00009-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c043a1935d4c9eb2d0c98836a0a357cee318d8c5b86d4c55dbd25c0e44cfe9
+size 4227859222

model-00010-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3c0004110f517cba02e72f4f512e74a36b354a44fb31dbeba3d9c979dfaa8
+size 4361585912

model-00011-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e962dcf20925e46dee157a111ffe986735503c06d246f9f47b80fbf6609c74
+size 5304780035

model-00012-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32ab0bb152675f4921406fa276035bbf177c2d2f7afb8ead846b22dcab5693f
+size 4227859228

model-00013-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2c8bb062c14edd3c342303343d68a179c88b46189026529fe2ce0a51d5ffb5
+size 4361585998

model-00014-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6b0561078b523bfb3a0ca15b353136893c8a0d8c9a32fc8f9395171184e211
+size 4361585928

model-00015-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3c520736b1289013b93969462fbebbc6bc78cbab4c5f904629de269e0bd7c0
+size 4227859228

model-00016-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308d957119d8f91f786d23d5929d1fd4159e9e80f31d99d39eb18858f9ec8cf4
+size 5304780104

model-00017-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e9c3ed1da1f5a2c417c2096025894ff9e0340fc409cb57683ea278843943b9
+size 4361585926

model-00018-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac32b976e617556bed7be51eaeb50eec666984f358edb1e20591a60ebf6566bf
+size 4227859224

model-00019-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656666829b795ef4ba3ce2052070debf7527bf7c5b250cd48505c968a3a12966
+size 4361586000

model-00020-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52323e4203f99edd60e4f4406ac8846958c5da1732cedee0e016a39621f485eb
+size 5304780072

model-00021-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cf196ac749fa3d15ea6fc22946556628c2cc042f1b1fe6ee7a95516f5f8229
+size 4227859228

model-00022-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b935218b05d0c381d33c67ab9a7d1392c937cf59cc96049579714feb2d2138
+size 4361585978

model-00023-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd1008c2f13a4f56360d09f49d3365d2408872f9ce4d1c881887ddf4cd47eb0
+size 4361585936

model-00024-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be08a7df3313eacad9b8bef61d9f5334d3ebf75fd2df88d7303613d5fcf4b46e
+size 4227859230

model-00025-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d065d0414d4aa53e06ec69036f262899878f6654104c36fdef139685c8fcc995
+size 5304780134

model-00026-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4702ac4764b17a503ea19c98114ced5880c0f8cc4a6848908ee814c85aa8d23
+size 4361585940

model-00027-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6762a8cb043441339f1a7cda8c7f6cb6ec923d3f2fc535f8741cba09ba546f
+size 4227859224

model-00028-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43ab57cc8c58232edf0314b6148afb7a48c0bad2965e2334ff1bf1057284048
+size 4361585990

model-00029-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f64269b94f5bc9a351291777f3616cef56a1a8696f0cfb8e4356d339ac72319
+size 5304780020

model-00030-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6d86b5705663025789512d39e136f9efaa8405ac578704226752a78adf7075
+size 4227859226

model-00031-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476b3158a5eec2868dc45b196eb0057586e436816491bc99637db5ceafb5a8be
+size 4361586024

model-00032-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71daf82179aa808d1a324cd0678f1130593bc6aa142d9e5e6fee4341a113578
+size 4361585970

model-00033-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441d8a2ca1f91d5b3c36f5836fc5fb3d46b8822aa48ec0e45b4a2fc85ad70580
+size 4227859222

model-00034-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30272f520a71353fadaae596baa35a6963895f2e4f7048363c0e237aa1ce14a
+size 5304780090

model-00035-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e00036dd4a2411b08b3f3bc130692906f4b51d4d22e11d198675710ce6b3e35
+size 4361585948

model-00036-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62d4a8b04a901e5782f6595db0fe076fdabe880c897f9182e0ed91b94810e73
+size 4227859228

model-00037-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22fe15ec7524148d95853024dbf282508844925e4302de460f72a9cf3d349a9
+size 4361586024

model-00038-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ceb54bf19341e4426cf17cb269aa4d0157e4705d89510fbb2508ba2a8de04cd
+size 5304780048

model-00039-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a82c5efe7fb5efce9e72dd46932b200d1b41f1ad6d665ff05a3d2909556b14
+size 4227859224

model-00040-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d67515eacb35122785575e5541b29a71b0381e8ab7a9f74e8a5e456531c9c2
+size 4361585964

model-00041-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87634c005b404ad8fe77945b2fa34681f1a962aab909d83e9070f15d7fc86cd2
+size 4361585926

model-00042-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa120c5ab73b19456f207ecc4e4b05828c62db86ba9501321fa204639bcb927
+size 4227859228

model-00043-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf931a69c97f9f7c4d0faf26d1a2b3b103eed18268f1e66c41d3330af7cad4bd
+size 5304780134

model-00044-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f6b555ec74b423fbd83d495db07a96f8dd76e3cedb9228aabfc866a8597556
+size 4361585962

model-00045-of-00088.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea381862c36d0804c9d4b536738ff26307e91fb5ebdbcf93f3d7e3e031c61ee
+size 4227859228