Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,28 @@
+MIT License
+
+Copyright 2025 MiniMax AI.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+Our only modification is that, if the Software (or any derivative works
+thereof) is used for any of your commercial products or services that have
+more than 100 million monthly active users, or more than 30 million US
+dollars (or equivalent in other currencies) in annual recurring revenue,
+you shall prominently display "MiniMax M2" on the user interface of such
+product or service.

README.md

@@ -0,0 +1,135 @@
+---
+license: other
+license_name: modified-mit
+tags:
+  - moe
+  - mixture-of-experts
+  - jangtq
+  - reap
+  - mlx
+  - minimax_m2
+pipeline_tag: text-generation
+library_name: mlx
+---
+
+# MiniMax-M2.7-Small-JANGTQ
+
+**This is now a ~138B-A10B MoE** (down from MiniMax M2's 230B base) —
+40% routed-expert prune + 2-bit JANGTQ quantization. Distilled from
+MiniMax M2 via our v3 calibration corpus + REAP saliency observer +
+JANGTQ2 codebook quantization.
+
+Runs on Apple Silicon via the JANG toolchain + MLX.
+
+## Pipeline
+
+```
+MiniMax M2 (base)
+    ↓  v3 calibration corpus  (24% code · 20% agentic · 20% general ·
+    ↓                          10% academic_mc · 8% science · 8% CN ·
+    ↓                          5% cyber · 3% systems · 2% longctx)
+    ↓
+REAP saliency observer (62 layers × 256 experts → scoring)
+    ↓  MiniMax-M2.7-Small = 40% expert prune (154 of 256 kept per layer)
+    ↓
+JANGTQ2 quantization
+    • 2-bit MXTQ on routed-expert weights (Hadamard-rotated codebook)
+    • 8-bit affine on attention + dense MLP + embed + lm_head
+    • 16-bit on norms and router weights
+```
+
+## Specs
+
+| | Value |
+|---|---|
+| Parameters | **~138B total, ~10B active per token** |
+| Routed experts kept | 154 of 256 (60%) |
+| Top-k active experts | 8 per token |
+| Layers | 62 |
+| Bundle size | 38 GB |
+| Dtype | bfloat16 activations |
+| Attention | Standard Q/K/V + GQA 6:1, head_dim=128, rope_theta=5M |
+| Context | 196,608 |
+
+## Use
+
+```python
+from jang_tools.load_jangtq import load_jangtq_model
+from mlx_lm import generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tokenizer = load_jangtq_model("JANGQ-AI/MiniMax-M2.7-Small-JANGTQ")
+
+messages = [{"role": "user", "content": "Write a Python function that…"}]
+prompt = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=False
+)
+
+# Interleaved-thinking / always-reasoning. Use MiniMax's
+# official sampling:  temp=1.0, top_p=0.95, top_k=40
+out = generate(model, tokenizer, prompt=prompt, max_tokens=4096,
+               sampler=make_sampler(temp=1.0, top_p=0.95, top_k=40))
+```
+
+## Calibration corpus (v3 mix)
+
+REAP saliency was computed over a 31,338-sample stratified English+CJK
+mix (~8.6 M tokens), bucketed to approximate typical JANGQ-AI workload:
+
+| Bucket | Share | Source datasets |
+|--------|-------|-----------------|
+| Coding (22%) | 7% · 6% · 4% · 3% · 2% | `ise-uiuc/Magicoder-OSS-Instruct-75K` · `nvidia/OpenCodeReasoning` · `m-a-p/CodeFeedback-Filtered-Instruction` · `HuggingFaceH4/CodeAlpaca_20K` · `iamtarun/python_code_instructions_18k_alpaca` |
+| Agentic (19%) | 7% · 5% · 3% · 2% · 2% | `NousResearch/hermes-function-calling-v1` · `glaiveai/glaive-function-calling-v2` · `lilacai/glaive-function-calling-v2-sharegpt` · `THUDM/AgentInstruct` (os) · `princeton-nlp/SWE-bench_oracle` |
+| General (17%) | 7% · 4% · 3% · 3% | `allenai/tulu-3-sft-mixture` · `open-thoughts/OpenThoughts-114k` · `teknium/OpenHermes-2.5` · `HuggingFaceH4/ultrachat_200k` |
+| Academic MC (11%) | 5% · 3% · 1% · 1% · 1% · 0.5% · 0.5% | `cais/mmlu` (all, auxiliary_train) · `TIGER-Lab/MMLU-Pro` · `allenai/ai2_arc` · `allenai/openbookqa` · `allenai/sciq` · `tau/commonsense_qa` · `bigbio/med_qa` |
+| Science (10%) | 4% · 3% · 1.5% · 1.5% | `AI-MO/NuminaMath-CoT` · `ccdv/arxiv-summarization` · `qiaojin/PubMedQA` · `camel-ai/physics` |
+| Chinese (9%) | 4% · 2.5% · 2.5% | `silk-road/alpaca-data-gpt4-chinese` · `wangrui6/Zhihu-KOL` · `YeungNLP/firefly-train-1.1M` |
+| Cybersec (5%) | 3% · 2% | `CyberNative/Code_Vulnerability_Security_DPO` · `Trendyol/cybersecurity-instruction-datasets` |
+| Long-context (3%) | 2% · 1% | `emozilla/pg19` · `ccdv/arxiv-summarization` (longer docs) |
+| Systems (3%) | 1.5% · 1.5% | `b-mc2/sql-create-context` · `cognitivecomputations/dolphin-coder` |
+
+Total ≈ 31,338 records ≈ 8.6 M tokens (GPT-4 tokenizer estimate).
+
+## Evaluation
+
+### HumanEval+ (code generation)
+
+- **Dataset**: `evalplus/humanevalplus` test split (same 164 prompts as
+  original HumanEval but with much harder test cases from EvalPlus).
+- **Protocol**: greedy pass@1 baseline + pass@5 retry on failures.
+- **Sampling for pass@5**: temp=1.0, top_p=0.95, top_k=40 (MiniMax
+  official recommended sampling); k=5 samples per failed problem, early
+  stop on first passing sample.
+- **Max tokens**: 800 (pass@1), 1200 (pass@5 retry).
+- **Grading**: each candidate executed as a subprocess with 20s timeout;
+  passes only if ALL EvalPlus tests pass.
+
+| Metric | Score |
+|--------|-------|
+| **pass@1 (greedy)** | **71.95%** (118/164) |
+| **pass@5 (greedy + sampled retry of failures)** | **89.02%** (146/164) |
+
+28 of the 46 greedy failures were recovered via sampling (temp=1.0,
+top_p=0.95, top_k=40); the remaining 18 are a mix of genuine logic
+errors (AssertionError) and prompts where even 1200 tokens ran out
+mid-reasoning (no_code_block).
+
+*Eval harness code*: see `jang_tools.kimi_prune.bench_humaneval` (pass@1) and `jang_tools.kimi_prune.bench_humaneval_passk` (pass@k retry on failures) in the [JANG toolchain](https://github.com/jinho-jang/jang).
+
+## Variants
+
+| Variant | Prune | Size | HF |
+|---------|-------|------|-----|
+| **MiniMax-M2.7-Small** | 40% | 38 GB | `JANGQ-AI/MiniMax-M2.7-Small-JANGTQ` |
+| MiniMax-M2.7-Med | 25% | ~48 GB | `JANGQ-AI/MiniMax-M2.7-Med-JANGTQ` *(pending)* |
+| MiniMax-M2.7-Large | 10% | ~57 GB | `JANGQ-AI/MiniMax-M2.7-Large-JANGTQ` *(pending)* |
+
+## Credits
+
+Base: MiniMax M2.
+Methodology: JANG toolchain — REAP saliency + JANGTQ codebook quantization.
+Release: JANGQ-AI (eric@jangq.ai).
+
+## License
+
+Modified MIT — inherited from MiniMax M2.

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 +1,105 @@
+{
+  "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": 0,
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "num_local_experts": 154,
+  "num_mtp_modules": 0,
+  "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": false,
+  "use_qk_norm": true,
+  "use_routing_bias": true,
+  "vocab_size": 200064,
+  "_name_or_path": "MiniMax-M2.7-Small",
+  "quantization": {
+    "group_size": 64,
+    "bits": 2
+  }
+}

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 +1,18 @@
+{
+  "weight_format": "mxtq",
+  "profile": "JANGTQ2",
+  "mxtq_seed": 42,
+  "source_model": "JANGQ-AI/MiniMax-M2.7-Small",
+  "source_config": {
+    "n_routed_experts": 154,
+    "num_hidden_layers": 62
+  },
+  "mxtq_bits": {
+    "routed_expert": 2,
+    "attention": 8,
+    "dense_mlp": 8,
+    "embed_tokens": 8,
+    "lm_head": 8,
+    "norms_router": 16
+  }
+}

model-00001-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d178f4a3b2dbdd1767cb9c86e2542fd3e2f33e18c1c2be68cec94bd1349291d
+size 1000475508

model-00002-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197f9f1c45042f4725d4bbcd489ddb719c8d6b07ea7813a975268129d451e991
+size 1000973812

model-00003-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c89d2c847b81ced36b81971be1bea6f292750fe9f2eb1dd8c5929fd086e79df
+size 1001374012

model-00004-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911ca4f1fa42bb836491224643fcdd563c6215d9aad5455d023e6b5f935d4ef7
+size 1000577732

model-00005-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1675164c3f3a47097a7f8d6819e4f706fa8ee56eaa3ed5cfbf2379b7ce45cad
+size 1001370964

model-00006-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b59facabba205773fd599b2509f77690ce07252d33228fbae71190e271a89ac
+size 1000976660

model-00007-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df94abb9fcf991fbf88cb71efba35c6b69f17322fc5947b7d550fe008c6ad6d
+size 1001371312

model-00008-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42087ca4b0776fa4366ce1c2477ccab1883ea56f18b11870347f60322fff839
+size 1000979696

model-00009-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3728e00331a41663642bd4ac6f59d94ec591fe901c643a6c570cdcbb8eb83451
+size 1003117616

model-00010-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c588e57ac2333433ed604871281529f05053449d7acb0403a2782e25021e39
+size 1000418572

model-00011-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89172f26bbc36a18e637689142ff6cb2becaedecd2e6a9d44ccff9a1350e477a
+size 1000580048

model-00012-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dfc2bd4f933e1bbfaa0f70ab5436dcbb77d7e95725313bc7ad5b3855c883f4
+size 1001375824

model-00013-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc17f03e5a201723ffb6e936ddd32c10ca13a98014f2bfe41b4dac73d7672fe6
+size 1000976624

model-00014-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b11d3810318db9192aa9691474176639eef9d90c59da5466a8f0eb41d5277f
+size 1001376372

model-00015-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0fb32ea37548e5d9fe02776e499ee310b8fbed77bb97577a62a8ffc6592b71
+size 1000975788

model-00016-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1cfe9dba2d1aa6805cd4ea046e16e37a6b01164ed17125561d37a97d6c809a6
+size 1001376256

model-00017-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d8545b02b500752b21e6b738ffdc02f9df96c5ca48d246fe015e9a40edce33
+size 1000976608

model-00018-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b90ca4ed76f6c46a4ed0c5329a3f66a534e0a59973e133b8cd52f5c1937c38d
+size 1000976472

model-00019-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c4991f64bbf99f93f1f5844b2b3ee1b9687198601b1150fae52682af4e47ca
+size 1000979664

model-00020-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0499737a23ba6d3704bb3b156267736527b807bbbe20fc1326e188cd123023
+size 1001373468

model-00021-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f3681e8f880cd3733c78b76dd809b14f524c64dc838b6298490454ed3697a75
+size 1000978804

model-00022-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f0130fe380799f7a12bd012eb681992a598a67f48ee34129c3388ee11cf2a1
+size 1001373628

model-00023-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942902a36ca7253c33154bb90b85123ab49df35cfd97e598b6c73c8fe803bd14
+size 1000979540

model-00024-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e871f30f14475ae9adf8ba402c63e29c3c68918b928a60ec52c87adb417b04
+size 1000976216

model-00025-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063893268ec4d98baa68ecc063c817d6d6e983eac4dabc57332ca8877fefef27
+size 1000976640

model-00026-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bfec3d53cda61635d1b8d3e708d572a5f93070a21b62f4e80dbf0a7d2bd2d7
+size 1000979576

model-00027-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2724a544a4be91e47ef7ca5ad758bf4b530beaadc68cb4b5efb0f70b349bcf6d
+size 1001372440

model-00028-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efcccce686618136a5edd55459d10e7207c5649a3bf8ab15801112844823a17a
+size 1001376620

model-00029-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98ffec74bc963d2b1aafbd29f5fb99a88690f581f952e199ba2fccbe88f0956
+size 1000976524

model-00030-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485cd7c87d7ea58b4f2dffdb5106ce861e2820676a91da23e88619950c3629e0
+size 1000979376

model-00031-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458976ab59c41f982c6250276eaebd67bbbe1293d873be36150ac44b5c605c11
+size 1003117316

model-00032-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170c64ee9c94d564cb6e0f058b5289b71d927892b9828d50a4012bb2fcbcccfb
+size 1001205636

model-00033-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfc2b60045350a64f33edf7937ac3c7f482250463afbc492fe0b75de72b977c
+size 1001376252

model-00034-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9d0727ddb08b120d0c439aa82d074ad01b8563e62588ae8f24f50befe0d6e2
+size 1000976052

model-00035-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fede48feeaf95e68556e216412238b98d60b83444ea875ea8cde853267d183c5
+size 1001376660

model-00036-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b719a912b1ac5e76c28285d95855f365c2ffe8030c1af3eee65c096bb27cc8
+size 1000976036

model-00037-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208b5e567b3c2cf90bdc0dc3bd1894720b925e00e1c2fab82fa03d2374b16c82
+size 1001376500

model-00038-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b176479503f78ffdfd763d58ccf92bffd0f9f9f17057d6d4c65c38ac9db709
+size 1000869364

model-00039-of-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b9972e893e1b7f8909064a641121ada4015dcdf5db0952745d27cd0432c67d
+size 388401988