Instructions to use MiniMaxAI/MiniMax-M1-40k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M1-40k with Transformers:

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

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M1-40k", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M1-40k", trust_remote_code=True, dtype="auto", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MiniMaxAI/MiniMax-M1-40k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M1-40k"
# 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-M1-40k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M1-40k

SGLang

How to use MiniMaxAI/MiniMax-M1-40k 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-M1-40k" \
    --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-M1-40k",
		"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-M1-40k" \
        --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-M1-40k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M1-40k with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M1-40k
```

QscQ commited on Jun 8, 2025

Commit

3a77662

1 Parent(s): b620f7e

change files

Browse files

Files changed (2) hide show

config.json +8 -11
model.safetensors.index.json +0 -0

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "MiniMaxText01ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "attn_type_list": [
@@ -86,24 +86,21 @@
     1
   ],
   "auto_map": {
-    "AutoConfig": "configuration_minimax_text_01.MiniMaxText01Config",
-    "AutoModelForCausalLM": "modeling_minimax_text_01.MiniMaxText01ForCausalLM"
   },
-  "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_text_01",
   "num_attention_heads": 64,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 80,
@@ -120,7 +117,7 @@
   "shared_moe_mode": "sigmoid",
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.45.2",
   "use_cache": true,
   "vocab_size": 200064
 }

 {
   "architectures": [
+    "AbabForCausalLM"
   ],
   "attention_dropout": 0.0,
   "attn_type_list": [
     1
   ],
   "auto_map": {
+    "AutoConfig": "configuration_abab.AbabConfig",
+    "AutoModelForCausalLM": "modeling_abab.AbabForCausalLM"
   },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 6144,
   "initializer_range": 0.02,
   "intermediate_size": 9216,
   "layernorm_full_attention_alpha": 3.5565588200778455,
   "layernorm_linear_attention_alpha": 3.5565588200778455,
   "layernorm_mlp_alpha": 3.5565588200778455,
+  "max_position_embeddings": 131072,
+  "model_type": "mixtral",
   "num_attention_heads": 64,
   "num_experts_per_tok": 2,
   "num_hidden_layers": 80,
   "shared_moe_mode": "sigmoid",
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "transformers_version": "4.49.0",
   "use_cache": true,
   "vocab_size": 200064
 }

model.safetensors.index.json CHANGED Viewed

The diff for this file is too large to render. See raw diff