Upload MiniMax-M2.7-JANG_4S

README.md

@@ -0,0 +1,51 @@
+---
+base_model: MiniMaxAI/MiniMax-M2.7
+library_name: mlx
+pipeline_tag: text-generation
+license: apache-2.0
+tags:
+- mlx
+- jang
+- jang-quantized
+- JANG_4S
+- mixed-precision
+- apple-silicon
+---
+
+# MiniMax-M2.7-JANG_4S
+
+JANG adaptive mixed-precision MLX quantization produced via [vmlx / jang-tools](https://github.com/jjang-ai/jangq).
+
+- **Quantization:** 4.03b avg, profile JANG_4S, method mse-all, calibration activations
+- **Profile:** JANG_4S
+- **Format:** JANG v2 MLX safetensors
+- **Compatible with:** vmlx, MLX Studio, oMLX (with JANG patch)
+
+## Usage
+
+### vmlx (recommended)
+
+```bash
+pip install 'vmlx[jang]'
+vmlx serve bearzi/MiniMax-M2.7-JANG_4S
+```
+
+### Python
+
+```python
+from jang_tools.loader import load_jang_model
+from mlx_lm import generate
+
+model, tokenizer = load_jang_model("bearzi/MiniMax-M2.7-JANG_4S")
+messages = [{"role": "user", "content": "Hello"}]
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))
+```
+
+## About JANG
+
+JANG (Jang Adaptive N-bit Grading) assigns different bit widths to different layer types — attention layers get more bits, MLP/expert layers compress harder. This preserves model coherence at aggressive compression levels where uniform quantization breaks down.
+
+See [JANG documentation](https://github.com/jjang-ai/jangq) and scores at [jangq.ai](https://jangq.ai).
+
+Comparative benchmarks and feedback welcome — please open a discussion.

chat_template.jinja

@@ -0,0 +1,159 @@
+{# ----------‑‑‑ special token variables ‑‑‑---------- #}
+{%- set toolcall_begin_token   = '<minimax:tool_call>'         -%}
+{%- set toolcall_end_token     = '</minimax:tool_call>'        -%}
+{#- Tool Rendering Functions ============================================== -#}
+{%- macro render_tool_namespace(namespace_name, tool_list) -%}
+{%- for tool in tool_list -%}
+<tool>{{ tool.function | tojson(ensure_ascii=False) }}</tool>
+{% endfor -%}
+{%- endmacro -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{ content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- System Message Construction ============================================ -#}
+{%- macro build_system_message(system_message) -%}
+    {%- if system_message and system_message.content -%}
+        {{- visible_text(system_message.content) }}
+    {%- else -%}
+        {%- if model_identity is not defined -%}
+            {%- set model_identity = "You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax." -%}
+        {%- endif -%}
+        {{- model_identity }}
+    {%- endif -%}
+    
+    {#- Handle current_date -#}
+    {%- if system_message and system_message.current_date -%}
+        {{- '\n' ~ 'Current date: ' + system_message.current_date }}
+    {%- endif -%}
+    {#- Handle current_location -#}
+    {%- if system_message and system_message.current_location -%}
+        {{- '\n' ~ 'Current location: ' + system_message.current_location }}
+    {%- endif -%}
+{%- endmacro -%}
+{#- Main Template Logic ================================================= -#}
+{#- Extract system message (only first message if it's system) -#}
+{%- set system_message = none -%}
+{%- set conversation_messages = messages -%}
+{%- if messages and messages[0].role == "system" -%}
+    {%- set system_message = messages[0] -%}
+    {%- set conversation_messages = messages[1:] -%}
+{%- endif -%}
+{#- Get the last user message turn, for interleved thinking -#}
+{%- set ns = namespace(last_user_index=-1) %}
+{% for m in conversation_messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{#- Render system message -#}
+{{- ']~!b[' ~ ']~b]system' ~ '\n' }}
+{{- build_system_message(system_message) }}
+{#- Render tools if available -#}
+{%- if tools -%}
+    {{- '\n\n' ~ '# Tools' ~ '\n' ~ 'You may call one or more tools to assist with the user query.\nHere are the tools available in JSONSchema format:' ~ '\n' }}
+    {{- '\n' ~ '<tools>' ~ '\n' }}
+    {{- render_tool_namespace("functions", tools) }}
+    {{- '</tools>' ~ '\n\n' }}
+{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\n' }}
+{{- '\n' ~ toolcall_begin_token }}
+<invoke name="tool-name-1">
+<parameter name="param-key-1">param-value-1</parameter>
+<parameter name="param-key-2">param-value-2</parameter>
+...
+</invoke>
+{{- '\n' ~ toolcall_end_token }}
+{%- endif -%}
+{{- '[e~[\n' }}
+
+{#- Render messages -#}
+{%- set last_tool_call = namespace(name=none) -%}
+{%- for message in conversation_messages -%}
+    {%- if message.role == 'assistant' -%}
+        {#- Only render reasoning_content if no user message follows -#}
+        {{- ']~b]ai' ~ '\n' }}
+
+        {%- set reasoning_content = '' %}
+        {%- set content = visible_text(message.content) %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].strip('\n').split('<think>')[-1].strip('\n') %}
+                {%- set content = content.split('</think>')[-1].strip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if reasoning_content and loop.index0 > ns.last_user_index -%}
+            {{- '<think>' ~ '\n' ~ reasoning_content ~ '\n' ~ '</think>' ~ '\n\n' }}
+        {%- endif -%}
+        {%- if content -%}
+            {{- content }}
+        {%- endif -%}
+        {%- if message.tool_calls -%}
+            {{- '\n' ~ toolcall_begin_token ~ '\n' }}
+
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<invoke name="' + tool_call.name + '">' }}
+                {% set _args = tool_call.arguments %}
+                {%- for k, v in _args.items() %}
+                {{- '<parameter name="' + k + '">' }}
+                {{- v | tojson(ensure_ascii=False) if v is not string else v }}
+                {{- '</parameter>' }}
+                {% endfor %}
+                {{- '</invoke>' ~ '\n' }}
+            {%- endfor -%}
+            
+            {{- toolcall_end_token}}
+            {%- set last_tool_call.name = message.tool_calls[-1].name -%}
+        {%- else -%}
+            {%- set last_tool_call.name = none -%}
+        {%- endif -%}
+        {{- '[e~[' ~ '\n' }}
+        
+    {%- elif message.role == 'tool' -%}
+    {%- if last_tool_call.name is none -%}
+        {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+    {%- endif -%}
+    {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}
+        {{- ']~b]tool' }}
+    {%- endif -%}
+    {%- if message.content is string -%}
+        {{- '\n<response>' }}
+        {{- message.content }}
+        {{- '</response>' }}
+    {%- else -%}
+        {%- for tr in message.content -%}
+            {{- '\n<response>' }}
+            {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}
+            {{- '\n</response>' }}
+        {%- endfor -%}
+    {%- endif -%}
+    {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}
+        {{- '[e~[\n' -}}
+    {%- endif -%}
+        
+    {%- elif message.role == 'user' -%}
+        {{- ']~b]user' ~ '\n' }}
+        {{- visible_text(message.content) }}
+        {{- '[e~[' ~ '\n' }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt -#}
+{%- if add_generation_prompt -%}
+{{- ']~b]ai' ~ '\n' ~ '<think>' ~ '\n' }}
+{%- endif -%}

config.json

@@ -0,0 +1,104 @@
+{
+  "architectures": [
+    "MiniMaxM2ForCausalLM"
+  ],
+  "attn_type_list": [
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
+    "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
+  },
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 196608,
+  "model_type": "minimax_m2",
+  "mtp_transformer_layers": 1,
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "num_local_experts": 256,
+  "num_mtp_modules": 3,
+  "qk_norm_type": "per_layer",
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 5000000,
+  "rotary_dim": 64,
+  "scoring_func": "sigmoid",
+  "shared_intermediate_size": 0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "use_mtp": true,
+  "use_qk_norm": true,
+  "use_routing_bias": true,
+  "vocab_size": 200064,
+  "quantization": {
+    "group_size": 128,
+    "bits": 4
+  }
+}

configuration_minimax_m2.py

@@ -0,0 +1,200 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/minimax_m2/modular_minimax_m2.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_minimax_m2.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# coding=utf-8
+# Copyright 2025 the HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from transformers.configuration_utils import PretrainedConfig
+
+
+class MiniMaxM2Config(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`MiniMaxM2Model`]. It is used to instantiate an
+    MiniMaxM2 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 MiniMaxM2-7B-v0.1 or MiniMaxM2-7B-Instruct-v0.1.
+
+    [minimax_m2ai/MiniMaxM2-8x7B](https://huggingface.co/minimax_m2ai/MiniMaxM2-8x7B)
+    [minimax_m2ai/MiniMaxM2-7B-Instruct-v0.1](https://huggingface.co/minimax_m2ai/MiniMaxM2-7B-Instruct-v0.1)
+
+    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 32000):
+            Vocabulary size of the MiniMaxM2 model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`MiniMaxM2Model`]
+        hidden_size (`int`, *optional*, defaults to 4096):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 14336):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 32):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        num_key_value_heads (`int`, *optional*, defaults to 8):
+            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, check out [this
+            paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `8`.
+        head_dim (`int`, *optional*, defaults to `hidden_size // num_attention_heads`):
+            The attention head dimension.
+        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*32`):
+            The maximum sequence length that this model might ever be used with. MiniMaxM2's sliding window attention
+            allows sequence of up to 4096*32 tokens.
+        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-05):
+            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*):
+            The id of the padding token.
+        bos_token_id (`int`, *optional*, defaults to 1):
+            The id of the "beginning-of-sequence" token.
+        eos_token_id (`int`, *optional*, defaults to 2):
+            The id of the "end-of-sequence" token.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether the model's input and output word embeddings should be tied.
+        rope_theta (`float`, *optional*, defaults to 1000000.0):
+            The base period of the RoPE embeddings.
+        sliding_window (`int`, *optional*):
+            Sliding window attention window size. If not specified, will default to `4096`.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        num_experts_per_tok (`int`, *optional*, defaults to 2):
+            The number of experts to route per-token, can be also interpreted as the `top-k` routing
+            parameter
+        num_local_experts (`int`, *optional*, defaults to 8):
+            Number of experts per Sparse MLP layer.
+        output_router_logits (`bool`, *optional*, defaults to `False`):
+            Whether or not the router logits should be returned by the model. Enabling this will also
+            allow the model to output the auxiliary loss. See [here]() for more details
+        router_aux_loss_coef (`float`, *optional*, defaults to 0.001):
+            The aux loss factor for the total loss.
+        router_jitter_noise (`float`, *optional*, defaults to 0.0):
+            Amount of noise to add to the router.
+
+    ```python
+    >>> from transformers import MiniMaxM2Model, MiniMaxM2Config
+
+    >>> # Initializing a MiniMaxM2 7B style configuration
+    >>> configuration = MiniMaxM2Config()
+
+    >>> # Initializing a model from the MiniMaxM2 7B style configuration
+    >>> model = MiniMaxM2Model(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "minimax_m2"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise",
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.block_sparse_moe.gate": "colwise_rep",  # we need to replicate here to correctly route experts
+        "layers.*.block_sparse_moe.experts.*.w1": "colwise",
+        "layers.*.block_sparse_moe.experts.*.w2": "rowwise",
+        "layers.*.block_sparse_moe.experts.*.w3": "colwise",
+    }
+    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=32000,
+        hidden_size=4096,
+        intermediate_size=14336,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=8,
+        head_dim=None,
+        hidden_act="silu",
+        max_position_embeddings=4096 * 32,
+        initializer_range=0.02,
+        rms_norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=1,
+        eos_token_id=2,
+        tie_word_embeddings=False,
+        rope_theta=1e6,
+        sliding_window=None,
+        attention_dropout=0.0,
+        num_experts_per_tok=2,
+        num_local_experts=8,
+        output_router_logits=False,
+        router_aux_loss_coef=0.001,
+        router_jitter_noise=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.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.sliding_window = sliding_window
+
+        # 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.attention_dropout = attention_dropout
+        self.head_dim = head_dim
+
+        self.num_experts_per_tok = num_experts_per_tok
+        self.num_local_experts = num_local_experts
+        self.output_router_logits = output_router_logits
+        self.router_aux_loss_coef = router_aux_loss_coef
+        self.router_jitter_noise = router_jitter_noise
+
+        self.use_qk_norm = kwargs.pop("use_qk_norm", False)
+        self.rotary_dim = kwargs.pop("rotary_dim", self.head_dim)
+        self.partial_rotary_factor = kwargs.pop("partial_rotary_factor", 1)
+        if self.head_dim is not None:
+            self.partial_rotary_factor = self.rotary_dim / self.head_dim
+
+        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,
+        )
+
+
+__all__ = ["MiniMaxM2Config"]

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 200019,
+  "do_sample": true,
+  "eos_token_id": 200020,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "top_k": 40,
+  "transformers_version": "4.46.1"
+}

jang_config.json

@@ -0,0 +1,47 @@
+{
+  "quantization": {
+    "method": "jang-importance",
+    "profile": "JANG_4S",
+    "target_bits": 4,
+    "actual_bits": 4.03,
+    "block_size": 128,
+    "calibration_method": "activations",
+    "quantization_method": "mse-all",
+    "scoring_method": "awq+hessian",
+    "bit_widths_used": [
+      4,
+      6
+    ],
+    "quantization_scheme": "asymmetric",
+    "quantization_backend": "mx.quantize",
+    "hadamard_rotation": false
+  },
+  "source_model": {
+    "name": "MiniMax-M2.7",
+    "dtype": "bfloat16",
+    "parameters": "227.6B"
+  },
+  "architecture": {
+    "type": "moe",
+    "attention": "gqa",
+    "has_vision": false,
+    "has_ssm": false,
+    "has_moe": true
+  },
+  "runtime": {
+    "total_weight_bytes": 460947456,
+    "total_weight_gb": 0.43
+  },
+  "capabilities": {
+    "reasoning_parser": "qwen3",
+    "tool_parser": "minimax",
+    "think_in_template": true,
+    "supports_tools": true,
+    "supports_thinking": true,
+    "family": "minimax_m2",
+    "modality": "text",
+    "cache_type": "kv"
+  },
+  "format": "jang",
+  "format_version": "2.0"
+}

model-00001-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15f69aaf7d01bba61575cbc30902c1a7a231d9faefd362350c186d83e2cd727
+size 968233712

model-00002-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f42a596600f804b1eba53e89556306cc7dde75ce1cb0a81ebbb7407f8078e64
+size 641728952

model-00003-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac4d5fba5c24d88111490770a8cc1fe4f4241fde78308a2eeb42bee5e434779
+size 676136712

model-00004-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a9747115defe98b688ea6d4b2ee20fd160f510a409e929d1bac44a0037adde
+size 641728960

model-00005-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4970c8b42d488aead3cf3990175fde5d5acb1f2ccf5daa7fadced552d5ee115b
+size 641728952

model-00006-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9fb6cae836e86e76e6c312b9f7918c163bac51d254c1781366fedb80cacbd8
+size 676136712

model-00007-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f952df9f47ecec8b1f38d16919d443ee5dd3eb53b1d1fe34e85210cbc9b7d3
+size 641728960

model-00008-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2018af0c9a7eb97b80a5fa79cfda3bdb0bf1f97588016190c3769060abfd5bc0
+size 641728952

model-00009-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6922fa2a1f4f93c6c69b50e9890f4d6650d5388c313897d462b0c418574e1b
+size 676136712

model-00010-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c744b415ae27b24ddf33a911064d3e75cd84333c6e61e33e2e852c5bf35108
+size 641728960

model-00011-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83973d8791045a9c995793804295b5152d39de6f2f9d0077406ef8268dfc51f
+size 641728952

model-00012-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04060f019943ed1c4ca80df7b0e9d61bf94aca5bc513f53751544cd34e6fe002
+size 676136712

model-00013-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa120275b4e0be6f828f602ec33ab2ed95da72345255c56e6f1d73e53f57dc6
+size 641728960

model-00014-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee273a04d5b29d4abee7ff0dc272cdfcb6fe821d05102a46631f6b41d23fb63c
+size 641728952

model-00015-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d0844f609601080e39c2962aeb7126853e58be3ce16bd6d77b9516bbc61048
+size 676136712

model-00016-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16defe4d7458be361cc3f4ccaba5b9f62453bbfe5a8570ffa4ea9fb886575ac
+size 641728960

model-00017-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78d2b1685079b0161b567b566e9de0d97ab9468528cf7250e5c4508fb5ebb32
+size 641728952

model-00018-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f966066fb83415db2326ca9c94d418e9a6a6675f196d8cf56335b9b08fc0d7
+size 676136712

model-00019-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e04a4bafcfb4a8f9259ce159bb637670d19d8f3d0c192c705f52d9a4e08613c
+size 641728960

model-00020-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4845472ccab9e5fc0da4a8cca11c2795d5046ee983f48d10959ffb95ddbbe0f8
+size 641728952

model-00021-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f7c13c283e67c786fe08f0489b01650cbc4a2a9b43922525298022c6cb851f
+size 676136712

model-00022-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10041ebf7fdb50a0391ad733c4b9b7b158e51eb165cca3c710bd4ec946c6cb26
+size 641728960

model-00023-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b1d624d937c48e6b36be34db27960bea9b6e62c3a8f37280e14611fa45c1e1
+size 641728952

model-00024-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b822c2339b3f9a9a8db1566273318e73cfcdf345eb6b175f3d46ef53417fb6
+size 676136712

model-00025-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53862e9cca41f6f919ca4376f71a34a407a1b5e897f5f02a6e0438424c1a9912
+size 641728960

model-00026-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76c42792d73f98f9766e729b3350dec0b60c3c683d57d7f31a7092729bb7106
+size 641728952

model-00027-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6992f5594a9010da86fe3fb6eee4162ab5bfd14ce7ab1dce18488f07aeb7c75d
+size 676136712

model-00028-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5045463da21d103b954acc54ce94855bcf32144509f17188420d223ffc1a1a18
+size 641728960

model-00029-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50af8ac9cae6e1bf315d9523fd4b0f1b1dadc4a7d0611f7b5c056ce98ead0db
+size 641728952

model-00030-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245dcbde01b1b09af9a94afa03a73a7d2089a38daa49ddea6c4395bae4f99769
+size 676136712

model-00031-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a98f4f1acad8ff0d80c31a15b4ac103a59e96999a065da0814a6fc6db890d3
+size 641728960

model-00032-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11673f8db3c9d0865b2a9f5de387c63951d1c6104bc0aebcf85d2e66b9e6f2c
+size 641728960

model-00033-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2985dd63e3d2f5aacf9aa5f340b43d25c78f4091ee511401c407ab4960ab9f96
+size 676136728

model-00034-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817178c6a2693f0b9bf3c1d59f869ed3691dd8344fddc2c57d8bc4929eae6276
+size 641728960

model-00035-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19ea93673cf8625c2a8b15c7d1f1405e1a4f228f1e25822f25db594bb154f8b
+size 641728960

model-00036-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc6bea0908648900b44b58f9b7f4291cdb7164264f9665d10781cddefd50953
+size 676136728

model-00037-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51863118cb3d3bd07cd794fcf65931d22902b58261d23dfae4034bbd0852381e
+size 641728960

model-00038-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0236c8e903ea428d8a8996e8261f91540eb1afacb11874de5e5140aae3dc0bd3
+size 641728960

model-00039-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d06cf1d13d60dd09950631186bca039384b31bc65c48d08b863a3f7c7be25b
+size 676136728

model-00040-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9123f4cefbef7e8f2ed1bd7fbc2ece94a5f5858b2c08459ea89a9a850e6c6849
+size 641728960

model-00041-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3083c35a9dc5f670ce447d9c1062d954365a5f70c005922610f24b634a19fb
+size 641728960

model-00042-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92d5d7ec5ebf856cc0f1b412d61f88c32a71ad8e2fd9cdef4be5e78c1cb2547
+size 676136728

model-00043-of-00187.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83ceec4a0dd5ae0a891cc292e6f67722ad59863e5daf04b37aa5b82854967e5
+size 641728960