Instructions to use morriszjm/MiniMax-M2.5-192e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use morriszjm/MiniMax-M2.5-192e with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="morriszjm/MiniMax-M2.5-192e", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("morriszjm/MiniMax-M2.5-192e", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("morriszjm/MiniMax-M2.5-192e", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use morriszjm/MiniMax-M2.5-192e with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "morriszjm/MiniMax-M2.5-192e"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morriszjm/MiniMax-M2.5-192e",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/morriszjm/MiniMax-M2.5-192e

SGLang

How to use morriszjm/MiniMax-M2.5-192e with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "morriszjm/MiniMax-M2.5-192e" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morriszjm/MiniMax-M2.5-192e",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "morriszjm/MiniMax-M2.5-192e" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "morriszjm/MiniMax-M2.5-192e",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use morriszjm/MiniMax-M2.5-192e with Docker Model Runner:
```
docker model run hf.co/morriszjm/MiniMax-M2.5-192e
```

MiniMax-M2.5-192e

Training-free expert-pruned variant of MiniMaxAI/MiniMax-M2, produced by the minimax_expert_pruning pipeline.

What changed

num_local_experts: 256 → 192 (pruning rate: 25.0 %)
All non-MoE tensors (attention, layernorms, embeddings, lm_head, MTP heads if any) are bit-identical to the source model.
gate.weight and e_score_correction_bias per MoE layer are row-sliced to the kept experts; per-expert tensors of dropped experts are absent; kept experts are renumbered contiguously to 0..191.
top_k = num_experts_per_tok is unchanged (8).

Method (one-paragraph)

We run a small calibration set (64 prompts spanning Nokia AI4Code, general English Q&A, multilingual, and reasoning) through the unpruned source model and hook every MoE layer's router. Per layer, we accumulate each expert's selected probability mass — the post-sigmoid routing weight that the expert receives, summed over all calibration tokens that selected it in their top-8. We keep the top-K by this score per layer (uniform K) and atomically slice the on-disk per-expert tensors. No gradients, no fine-tuning.

Layer-level statistics

Layers covered: 62
Tokens per layer (calibration): 1,851
Calibration prompts by bucket: {"ai4code": 1008, "general_en": 416, "reasoning": 257, "multilingual": 170}
Median per-layer "kept-min vs drop-max" routing-mass gap: +0.0227 (positive = clean separation between the kept and dropped experts; close to zero or negative = experts of similar utility, expect more quality risk)

Intended use

Production-style serving of the source model's domain (Nokia / Merlin AI4Code plus general English) at reduced HBM footprint. Expect graceful quality degradation versus the unpruned source on tasks well-covered by the calibration mix; quality on out-of-distribution domains may drop further.

Limitations

Training-free: no fine-tune recovery, no distillation, no merge.
Uniform K per layer: late layers may tolerate more pruning than early ones, unexploited here.
Calibration mix is small (64 prompts). Domain coverage is biased toward the included buckets.

Files

config.json, model-NNNNN-of-NNNNN.safetensors (FP8), model.safetensors.index.json, tokenizer, custom modeling_minimax_m2.py + configuration_minimax_m2.py, and expert_prune_plan.json (full record of which experts were kept per layer).

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tok = AutoTokenizer.from_pretrained("morriszjm/MiniMax-M2.5-192e", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "morriszjm/MiniMax-M2.5-192e", trust_remote_code=True,
    torch_dtype=torch.bfloat16, device_map="auto",
)

For vLLM serving, pass --trust-remote-code and (on multi-GPU) match --data-parallel-size to the EP topology you compiled the K against.

Downloads last month: 95

Safetensors

Model size

173B params

Tensor type

F32

BF16

F8_E4M3

Model tree for morriszjm/MiniMax-M2.5-192e

Base model

MiniMaxAI/MiniMax-M2

Quantized

(47)

this model