Instructions to use QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ

SGLang

How to use QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ 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 "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ" \
    --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": "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ",
		"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 "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ" \
        --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": "QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/MiniMax-M2-REAP-162B-A10B-AWQ
```

MiniMax-M2-REAP-162B-A10B-AWQ / config.json

JunHowie

Add files using upload-large-folder tool

727bc6d verified 11 months ago

Raw History Blame Contribute Delete

3.16 kB

	{
	"name_or_path": "tclf90/MiniMax-M2-REAP-162B-A10B-AWQ",
	"architectures": [
	"MiniMaxM2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"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"
	},
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": null,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 1536,
	"layernorm_full_attention_beta": 1.0,
	"layernorm_linear_attention_beta": 1.0,
	"layernorm_mlp_beta": 1.0,
	"max_position_embeddings": 196608,
	"mlp_intermediate_size": 8192,
	"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": 180,
	"num_mtp_modules": 3,
	"output_router_logits": false,
	"partial_rotary_factor": 0.5,
	"qk_norm_type": "per_layer",
	"quantization_config": {
	"quant_method": "awq",
	"bits": 4,
	"group_size": 128,
	"version": "gemm",
	"zero_point": true,
	"modules_to_not_convert": [
	"model.layers.0.",
	"model.layers.1.self_attn",
	"model.layers.2.self_attn",
	"model.layers.3.self_attn",
	"model.layers.4.self_attn",
	"model.layers.5.self_attn",
	"model.layers.6.self_attn",
	"model.layers.7.self_attn",
	"model.layers.8.self_attn",
	"model.layers.9.self_attn",
	"model.layers.10.self_attn",
	"model.layers.11.self_attn",
	"model.layers.12.self_attn",
	"model.layers.13.self_attn",
	"model.layers.14.self_attn",
	"model.layers.15.self_attn",
	"model.layers.47.self_attn",
	"model.layers.48.self_attn",
	"model.layers.49.self_attn",
	"model.layers.50.self_attn",
	"model.layers.51.self_attn",
	"model.layers.52.self_attn",
	"model.layers.53.self_attn",
	"model.layers.54.self_attn",
	"model.layers.55.self_attn",
	"model.layers.56.self_attn",
	"model.layers.57.self_attn",
	"model.layers.58.self_attn",
	"model.layers.59.self_attn",
	"model.layers.60.self_attn",
	"model.layers.61.self_attn"
	]
	},
	"rms_norm_eps": 1e-06,
	"rope_theta": 5000000,
	"rotary_dim": 64,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"scoring_func": "sigmoid",
	"shared_intermediate_size": 0,
	"shared_moe_mode": "sigmoid",
	"sliding_window": null,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"use_mtp": true,
	"use_qk_norm": true,
	"use_routing_bias": true,
	"vocab_size": 200064,
	"torch_dtype": "float16"
	}