Instructions to use QSILY/MiniMax-M2.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QSILY/MiniMax-M2.7 with Transformers:

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

pipe = pipeline("text-generation", model="QSILY/MiniMax-M2.7", 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("QSILY/MiniMax-M2.7", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QSILY/MiniMax-M2.7", 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 QSILY/MiniMax-M2.7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QSILY/MiniMax-M2.7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QSILY/MiniMax-M2.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QSILY/MiniMax-M2.7

SGLang

How to use QSILY/MiniMax-M2.7 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 "QSILY/MiniMax-M2.7" \
    --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": "QSILY/MiniMax-M2.7",
		"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 "QSILY/MiniMax-M2.7" \
        --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": "QSILY/MiniMax-M2.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QSILY/MiniMax-M2.7 with Docker Model Runner:
```
docker model run hf.co/QSILY/MiniMax-M2.7
```

MiniMax-M2.7 / config.json

QSILY

Duplicate from MiniMaxAI/MiniMax-M2.7

a0541e1 27 days ago

raw

history blame contribute delete

1.68 kB

	{
	"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": 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": {
	"activation_scheme": "dynamic",
	"fmt": "float8_e4m3fn",
	"quant_method": "fp8",
	"weight_block_size": [
	128,
	128
	],
	"modules_to_not_convert": [
	"gate",
	"e_score_correction_bias",
	"lm_head"
	]
	},
	"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
	}