Upload MLX converted model with quantization settings

README.md

@@ -0,0 +1,41 @@
+---
+license: other
+license_name: modified-mit
+library_name: transformers
+base_model: moonshotai/Kimi-K2-Instruct-0905
+tags:
+- mlx
+---
+
+# cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6
+
+The Model [cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6](https://huggingface.co/cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6) was converted to MLX format from [moonshotai/Kimi-K2-Instruct-0905](https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905) using mlx-lm version **0.28.0**.
+
+## Quantization Details
+
+This model was converted with the following quantization settings:
+
+- **Quantization Strategy**: mixed_2_6 (Mixed precision)
+- **Average bits per weight**: 3.146
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_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 +1,46 @@
+{%- 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 -%}

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-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c1cb5d2ca6260a5f977366e4113a10d7eb9b11dfb0a41d5a387e6b78a156c84
+size 4143384830

model-00002-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0116380da643a0711a1fae51884c167857425adb256a83118ad2624d3145ef5f
+size 4638426467

model-00003-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cdc0b243a00543def0e4b71a6a68eef30e803271709e0a0f5a8d42b59a12dba
+size 3523216150

model-00004-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d94b940afc2104942b1fe82eb97e8c8a52fd84a45e9a6595a9840ce26e7133
+size 4638426523

model-00005-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe413225dd654b03741d78e357f1d00ab0506bfe9a320ffac4dfb892c73ab88d
+size 3523216144

model-00006-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a87bbd3fcfa82be477c23b76af1b5569c6fe6d84ff95cbc8f396d5dd9a07a6e
+size 4638426481

model-00007-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9709a35fa9d559a2e58072092df01663529aa1a6cf6e860dd0d25452ba0b66bb
+size 3523216150

model-00008-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c510e8805edadfcd135ffe547002fa43244e6e9e1ecee94682c50f4cd1c6279c
+size 4638426471

model-00009-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:489609f57ce8b7c46be2449ac516b4f65548178149c670dbf34eea8e5210e76b
+size 3523216148

model-00010-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26191494268736ccce7c83259cf0c404eacb237a977b4fc3639368d4e8f7cbd6
+size 4638426477

model-00011-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6847db489dec82cae08ad8a95b1f73b6155860d910fc2242fff2eb1eec86ec3
+size 3523216146

model-00012-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:719d2b8c5b9594705b7489204aa25a0cc4bcb0969d21a4d6be0adf996a42737e
+size 4638426495

model-00013-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0800f1c4d15eb28a2c663d93eaf8b88813dd38f1617b369989496236bb54ef
+size 5335730261

model-00014-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8c335942baf846bcc0b44f1953e11a7106de1830ef974512298e3a7a9dd763
+size 5335730293

model-00015-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b27e5e1af7b0bef56661b0d8a43989b85561250ceb2ea0a0956c0325ff598ce7
+size 3523216148

model-00016-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465bc3ca8e28943e1b5ee6311895cb87f9e393c90a5da5c201a03d3eed14e4f8
+size 4638426490

model-00017-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a484766296fa17de3bfec28676e7be22c7a0ca787c03134f65441b17cc530f
+size 5335730270

model-00018-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75124c521b5b38321d8fda10c1f9b0e319c63ec7025866140d383a1d4a785d88
+size 5335730314

model-00019-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2de9422e8adcb923aa83e6077c8f7c1b7b2e3e24ace4a13824081fd0b54eac
+size 3523216156

model-00020-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae7865c031727113039403a6344734a6c1c47018e1747fb82ab94255c5ced84
+size 4638426534

model-00021-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8393a439ac884112162af7de4691782ea632766261d48c9052735497723037ca
+size 5335730338

model-00022-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a012687e9e205e3f1b77e68daa16f0b000532eeccdff02c2e32298c7688d42b3
+size 5335730302

model-00023-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8092bc6e8ba40b23d77e134105d19713a4fcf05781f5273311c1556746a278b4
+size 3523216150

model-00024-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755804a6767195fd2adf8f6a064962295ee7ffb2e04e706465c45779815d4572
+size 4638426524

model-00025-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4938d3f405bf59ed4cc849823780fd21d4c4fc2ef7397a44ff735b6e910d9520
+size 5335730316

model-00026-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545bc4c31d379276fb2888410b94113e99dcd8b5cae5bf63f13ede9e49a8a696
+size 5335730332

model-00027-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ada37ee5a30cfae3e70466e4da8f53039e6fd097bcabad9d1b1ba0634ede9c
+size 3523216158

model-00028-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71a42edb95128095a271f501b551d93eec63619a342cd105c4da4b4502abe88
+size 4638426480

model-00029-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d107910a2927caa4d2f13c5f9ccb8ad0e38b7dc96319ac7f847112c8e021c1f
+size 5335730354

model-00030-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1acea7a32954b79c9fd0bedd0b810fe8c174f3e72a9ec877b57fc31d25150bb
+size 5335730306

model-00031-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93cffafe2b52890f9bdd0105bb8f43743c74fdb9c4b4287bd38991fa8d169a95
+size 3523216150

model-00032-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd8d2f052824155841b280eb26652f5566e45186f19a47a91db53c2245ca687
+size 4638426510

model-00033-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eae2fcac32287116a124bf61229c988c2d3e5ed6f9026b90eadb3469723c972
+size 5335730288

model-00034-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a009fcdded01dce38754d517aaa1387ad7703f59ade8651e57a77aad27648034
+size 5335730336

model-00035-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356ba5a0264072e3ff6ff218b24065b097741387756dd80ed6e62293bb0ca06d
+size 3523216150

model-00036-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b140f09269facdd8b8ec1024af2e198b50dea19264de9c9f61f8f66c937d731
+size 4638426492

model-00037-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06c04679561098bb49fa881cc212e5a0c07e4673d4596aaef5fd3cc0a4261fa
+size 5335730318

model-00038-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4b53975efe8f42e7b16fb2d2cd2a4cc2dfe57870fdebcda78bf58051355e5a
+size 5335730320

model-00039-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8cea975871301dbd55918bb387bae92a6da659515e5ea7ac35a7775ef2b0bf
+size 3523216156

model-00040-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7a3e4828e7184b7accb8ac48c010a6621cc1f8775b6c28263b5a2e6c13b7b7
+size 4638426518

model-00041-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9770047a50c9ef420e6ccd636eee443c6e4550f79abd4dcb628b7466f06814
+size 5335730332

model-00042-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b0b4deda164ca594cd30b0cfe2f36a6aea42b0bee62a4867bb7deafd7e4917
+size 5335730340

model-00043-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f04040402046a8721769bde1c0c5f7755e8f18e08d904e6663b33412363a13
+size 3523216156

model-00044-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b49ab5c1f4f4f8ac4ee7c164c36110e0b13d0ee9e1425c65901b753e633ccf
+size 4638426526

model-00045-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809e681378dbb5269590ba7cadafed54f161da46ffbec296a4524b0d64c403a1
+size 5335730342