Instructions to use MiniMaxAI/MiniMax-M1-80k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M1-80k with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M1-80k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M1-80k", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiniMaxAI/MiniMax-M1-80k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M1-80k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniMaxAI/MiniMax-M1-80k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M1-80k

SGLang

How to use MiniMaxAI/MiniMax-M1-80k 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 "MiniMaxAI/MiniMax-M1-80k" \
    --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": "MiniMaxAI/MiniMax-M1-80k",
		"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 "MiniMaxAI/MiniMax-M1-80k" \
        --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": "MiniMaxAI/MiniMax-M1-80k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M1-80k with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M1-80k
```

MiniMax-M1-80k / config.json

sriting

upload config files

f8a8008 11 months ago

raw

history blame

1.87 kB

	{
	"architectures": [
	"MiniMaxM1ForCausalLM"
	],
	"attention_dropout": 0.0,
	"attn_type_list": [
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	1
	],
	"auto_map": {
	"AutoConfig": "configuration_minimax_m1.MiniMaxM1Config",
	"AutoModelForCausalLM": "modeling_minimax_m1.MiniMaxM1ForCausalLM"
	},
	"bos_token_id": null,
	"eos_token_id": null,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"initializer_range": 0.02,
	"intermediate_size": 9216,
	"layernorm_full_attention_alpha": 3.5565588200778455,
	"layernorm_full_attention_beta": 1.0,
	"layernorm_linear_attention_alpha": 3.5565588200778455,
	"layernorm_linear_attention_beta": 1.0,
	"layernorm_mlp_alpha": 3.5565588200778455,
	"layernorm_mlp_beta": 1.0,
	"max_position_embeddings": 10240000,
	"model_type": "minimax_m1",
	"num_attention_heads": 64,
	"num_experts_per_tok": 2,
	"num_hidden_layers": 80,
	"num_key_value_heads": 8,
	"num_local_experts": 32,
	"output_router_logits": false,
	"postnorm": true,
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000000,
	"rotary_dim": 64,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"shared_intermediate_size": 0,
	"shared_moe_mode": "sigmoid",
	"sliding_window": null,
	"tie_word_embeddings": false,
	"transformers_version": "4.45.2",
	"use_cache": true,
	"vocab_size": 200064
	}