Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,56 @@
+{
+  "</minimax:tool_call>": 200053,
+  "</think>": 200051,
+  "<add_file>": 200036,
+  "<code_context>": 200043,
+  "<code_interpreter>": 200023,
+  "<commit_after>": 200018,
+  "<commit_before>": 200016,
+  "<commit_message>": 200040,
+  "<commit_msg>": 200017,
+  "<delete_file>": 200037,
+  "<edit_file>": 200039,
+  "<empty_output>": 200015,
+  "<empty_source_file>": 200041,
+  "<file_content>": 200044,
+  "<file_sep>": 200049,
+  "<filename>": 200006,
+  "<filepath>": 200048,
+  "<fim_middle>": 200002,
+  "<fim_pad>": 200004,
+  "<fim_prefix>": 200001,
+  "<fim_suffix>": 200003,
+  "<function_call>": 200022,
+  "<gh_stars>": 200007,
+  "<issue_closed>": 200010,
+  "<issue_comment>": 200009,
+  "<issue_start>": 200008,
+  "<jupyter_code>": 200013,
+  "<jupyter_error>": 200035,
+  "<jupyter_output>": 200014,
+  "<jupyter_start>": 200011,
+  "<jupyter_text>": 200012,
+  "<minimax:tool_call>": 200052,
+  "<pr_start>": 200046,
+  "<rename_file>": 200038,
+  "<repo_struct>": 200042,
+  "<reponame>": 200005,
+  "<review_comment>": 200047,
+  "<source_files>": 200045,
+  "<think>": 200050,
+  "[e~[": 200020,
+  "]!d~[": 200021,
+  "]!p~[": 200000,
+  "]<]end of image[>[": 200030,
+  "]<]end of speech[>[": 200028,
+  "]<]end of video[>[": 200032,
+  "]<]image[>[": 200025,
+  "]<]speech[>[": 200024,
+  "]<]start of image[>[": 200029,
+  "]<]start of speech[>[": 200027,
+  "]<]start of video[>[": 200031,
+  "]<]video[>[": 200026,
+  "]<]vision pad[>[": 200033,
+  "]~!b[": 200034,
+  "]~b]": 200019
+}

chat_template.jinja

@@ -0,0 +1,165 @@
+{# ----------‑‑‑ 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 -%}
+    {%- elif content is none -%}
+        {{- '' }}
+    {%- 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-M2.1 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}}
+            {%- if message.tool_calls[-1].function -%}
+                {%- set last_tool_call.name = message.tool_calls[-1].function.name -%}
+            {%- else -%}
+                {%- set last_tool_call.name = message.tool_calls[-1].name -%}
+            {%- endif -%}
+        {%- 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 +1,223 @@
+{
+  "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"
+  },
+  "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",
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "format": "mixed-precision",
+    "quantization_status": "compressed",
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear",
+          "re:.*self_attn\\.(k|q|o|v)_proj$",
+          "re:.*self_attn\\.qkv_proj$"
+        ],
+        "weights": {
+          "type": "float",
+          "num_bits": 8,
+          "strategy": "block",
+          "block_structure": [
+            128,
+            128
+          ],
+          "symmetric": true,
+          "dynamic": false
+        },
+        "input_activations": {
+          "type": "float",
+          "num_bits": 8,
+          "strategy": "token",
+          "symmetric": true,
+          "dynamic": true
+        },
+        "format": "float-quantized"
+      },
+      "group_1": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear",
+          "re:.*block_sparse_moe\\.experts\\.\\d+\\.(w1|w2|w3)$"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "ignore": [
+      "model.layers.0.block_sparse_moe.gate",
+      "model.layers.1.block_sparse_moe.gate",
+      "model.layers.2.block_sparse_moe.gate",
+      "model.layers.3.block_sparse_moe.gate",
+      "model.layers.4.block_sparse_moe.gate",
+      "model.layers.5.block_sparse_moe.gate",
+      "model.layers.6.block_sparse_moe.gate",
+      "model.layers.7.block_sparse_moe.gate",
+      "model.layers.8.block_sparse_moe.gate",
+      "model.layers.9.block_sparse_moe.gate",
+      "model.layers.10.block_sparse_moe.gate",
+      "model.layers.11.block_sparse_moe.gate",
+      "model.layers.12.block_sparse_moe.gate",
+      "model.layers.13.block_sparse_moe.gate",
+      "model.layers.14.block_sparse_moe.gate",
+      "model.layers.15.block_sparse_moe.gate",
+      "model.layers.16.block_sparse_moe.gate",
+      "model.layers.17.block_sparse_moe.gate",
+      "model.layers.18.block_sparse_moe.gate",
+      "model.layers.19.block_sparse_moe.gate",
+      "model.layers.20.block_sparse_moe.gate",
+      "model.layers.21.block_sparse_moe.gate",
+      "model.layers.22.block_sparse_moe.gate",
+      "model.layers.23.block_sparse_moe.gate",
+      "model.layers.24.block_sparse_moe.gate",
+      "model.layers.25.block_sparse_moe.gate",
+      "model.layers.26.block_sparse_moe.gate",
+      "model.layers.27.block_sparse_moe.gate",
+      "model.layers.28.block_sparse_moe.gate",
+      "model.layers.29.block_sparse_moe.gate",
+      "model.layers.30.block_sparse_moe.gate",
+      "model.layers.31.block_sparse_moe.gate",
+      "model.layers.32.block_sparse_moe.gate",
+      "model.layers.33.block_sparse_moe.gate",
+      "model.layers.34.block_sparse_moe.gate",
+      "model.layers.35.block_sparse_moe.gate",
+      "model.layers.36.block_sparse_moe.gate",
+      "model.layers.37.block_sparse_moe.gate",
+      "model.layers.38.block_sparse_moe.gate",
+      "model.layers.39.block_sparse_moe.gate",
+      "model.layers.40.block_sparse_moe.gate",
+      "model.layers.41.block_sparse_moe.gate",
+      "model.layers.42.block_sparse_moe.gate",
+      "model.layers.43.block_sparse_moe.gate",
+      "model.layers.44.block_sparse_moe.gate",
+      "model.layers.45.block_sparse_moe.gate",
+      "model.layers.46.block_sparse_moe.gate",
+      "model.layers.47.block_sparse_moe.gate",
+      "model.layers.48.block_sparse_moe.gate",
+      "model.layers.49.block_sparse_moe.gate",
+      "model.layers.50.block_sparse_moe.gate",
+      "model.layers.51.block_sparse_moe.gate",
+      "model.layers.52.block_sparse_moe.gate",
+      "model.layers.53.block_sparse_moe.gate",
+      "model.layers.54.block_sparse_moe.gate",
+      "model.layers.55.block_sparse_moe.gate",
+      "model.layers.56.block_sparse_moe.gate",
+      "model.layers.57.block_sparse_moe.gate",
+      "model.layers.58.block_sparse_moe.gate",
+      "model.layers.59.block_sparse_moe.gate",
+      "model.layers.60.block_sparse_moe.gate",
+      "model.layers.61.block_sparse_moe.gate",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "global_compression_ratio": null,
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.1.dev0+g797d301.d20251228"
+  },
+  "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
+}

configuration_minimax_m2.py

@@ -0,0 +1,214 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           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,
+        )
+
+    def __repr__(self):
+        """
+        Overriding __repr__ to ensure that quantization_config does not contain Enum objects.
+        This prevents SyntaxError in torch.fx generated code which relies on repr() of the config.
+        """
+        print("Config sanitized in configuration_minimax_m2.py")
+        q_config = getattr(self, "quantization_config", None)
+        if isinstance(q_config, dict):
+            for k, v in list(q_config.items()):
+                if hasattr(v, "value"):
+                    # Replace Enum with its value
+                    q_config[k] = v.value
+                    print(f"  Enum: q_config[{k}] = {v.value}")
+        return super().__repr__()
+
+__all__ = ["MiniMaxM2Config"]

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 200019,
+  "do_sample": true,
+  "eos_token_id": 200020,
+  "top_k": 40,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00000-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb9b6d02da44140a22e421b4bc4a958874836181e5251522f0eb19c5056fe58
+size 2635579896

model-00001-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b2739ac4eb4978f54fdd4fe534c6be206aeeeb05b8e4c53d4177096bf48d87
+size 679579608

model-00002-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13cb97fc90f3eaa3244b5e7001480fc8f2aeba820db41f5b00e2310cfb9af4c
+size 1406386576

model-00003-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05cb968e8d223efabce0d4d7032d1fa5eeabb8eb524cfdc6541971342fe5cfe
+size 679579608

model-00004-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142bafcc2ecbac83d191831d7f76f14582d6bdd927c6a6a4850ce99712a0a7e6
+size 1406386576

model-00005-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978284cf5ef0d43142bb5aca2d4265aa88dbbb19b85d4a375716431bc4e44bd3
+size 679579608

model-00006-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf3b3479856a2c6e2063ff28ad670e42fbafb18da83783d6badfa19a9a3a860
+size 1406386576

model-00007-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993efeb0903c076600c4181d1c761cc6890a29420eef09e315b7050855fb54fd
+size 679579608

model-00008-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89a59fcb6b68132774f4b91470d3d07b3c5be83ab335eefd276a7e82a5047fd
+size 1406386576

model-00009-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8759476d8bd4dd162e513c522f8af6449885bc180023b86d5e4a8a74be970ec5
+size 679579608

model-00010-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f79cb22c4d59dc0d3ec02832529bec1129d2010acda34821b97d42ad1e65c77
+size 1406386576

model-00011-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865696447cec428da2cdc63ad3edbe1f1f91d15a3ae8d524a07ccc919cafe484
+size 679579608

model-00012-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5004d60ef7bebf9369a0c840b423d77ba081e4d134d7887fd6ae9ea183ba75
+size 1406386576

model-00013-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e546a597795380ef9c181f6aa84126b45beb46bd7701d4188cafa172d65fb8e6
+size 679579608

model-00014-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a87fba65c6d953987cc3ff550fa063715fba20cd7c43c5bf21bf0f456c6d351
+size 1406386576

model-00015-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e313401b649f4c02a3b21b3037132384ecc2350889272e99d8ef02d7b5b9c1cb
+size 679579608

model-00016-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a9bf695a3eca2c50d3d34faa2cccf6e1491b364dac9436697eaf628bdd9572
+size 1406386576

model-00017-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3568bfc90163e3ad507946611bcdce8d5a1813a428bc3c8991d8c158df8a1e82
+size 679579608

model-00018-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721656b73c52e06052a3d4bce67fdb95319471e67f49db7f72dc82d8ffd56d75
+size 1406386576

model-00019-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c5d36dc72b1424c2666a1ba99a3751241e9922ee79df8996b4eb55eff4b86f
+size 679579608

model-00020-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f069ef068a89e6cfe46a8fb446252b1608ee43c0936a8d3d8f2ace3323e825d
+size 1406388128

model-00021-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e2a1c5d6288cf1f3b3ed038e46bd4137a4ed250f4f956d668131b2fccfcbf2
+size 679580376

model-00022-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495dc76bb04bc23a7f4fdc038841412582a9d9a9d45439bea19c6a22eca3327c
+size 1406388128

model-00023-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f5f8d0af589df58f737218b790a45d0d6eb3d8198b0e69814bae1e5c0c58f9
+size 679580376

model-00024-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a21f6150ff68ce9fae443648d669ad988681613f641e6c845595bbc857ad3b
+size 1406388128

model-00025-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1538382239e15bd07588bf67b44151055041e429c57c06936b3d3c70af9157bc
+size 679580376

model-00026-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bad2b9c05ddc717cb370f01438eda5f052ce0e2dc7b4b0e016500af0681a074
+size 1406388128

model-00027-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba134558371bd18532abb8cd7496d10e9aec4afb24eef4628176f52d86ed9435
+size 679580376

model-00028-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b806437a67a0cf3b47ef809591c0f82a31725db6db8a97ac71cda3eb3034ea15
+size 1406388128

model-00029-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6c0f9b6e3d407ea64d98cdd19112385bf0323a20518f279cc641309c4fea82
+size 679580376

model-00030-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4609bfa4bde5c727850f1db88d8d9eb323cd9da4865e81232ed752ac7232f0f1
+size 1406388128

model-00031-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d209e93c55fb8708befa0e208d74ed32c2e4f051b68ff84df90e30e218c9db2
+size 679580376

model-00032-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d553d47dcac41b17e20a78519f6cb80a8801ec878ffdcae24b10fec879ae8a96
+size 1406388128

model-00033-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41af174c967f5e2773bacad3b530b79665b10f26e1ff5d5b97e3aab7ce3ae6f0
+size 679580376

model-00034-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dd4c3b3541bbe7d5f74c96cacdac36043e1ce8d53bf9a0719ac15ee7a988bd
+size 1406388128

model-00035-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62eabe5a12b54b6056edf096df6bcecda8e17af00e9cc1eb79170a24c92822c3
+size 679580376

model-00036-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a32b42bb61cf3ac2ab3a1370ff3341bd9249f228de4c22a0fe2816a7ba0af93f
+size 1406388128

model-00037-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f63260140d6f5bff42c333b9b178fadae496c50abb1b84c60cd341490b832f3
+size 679580376

model-00038-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f68c9d67383106bc82c013e7fececfbbfde8e806cd651771bd08f87835ad421
+size 1406388128

model-00039-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11c712a761ebf5e873284f450407ac538641fc27e6827638a990cdbab45112c
+size 679580376

model-00040-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62502ae6fbaaf20bd79179b9951afd8b9caab7a4ccc94efa4fbb4f61b46ea28
+size 1406388128

model-00041-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d185d5b2cf8536c499c7c06888b905f56f3338c84f55825da050184597cbe1f
+size 679580376

model-00042-of-00125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b38a479f4a0818e2955d50df7e332051458ef040eae68b74c9a48175a89b4e
+size 1406388128