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

Libraries

How to use RedHatAI/MiniMax-M2.5 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/MiniMax-M2.5", 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("RedHatAI/MiniMax-M2.5", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("RedHatAI/MiniMax-M2.5", 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 RedHatAI/MiniMax-M2.5 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RedHatAI/MiniMax-M2.5

SGLang

How to use RedHatAI/MiniMax-M2.5 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 "RedHatAI/MiniMax-M2.5" \
    --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": "RedHatAI/MiniMax-M2.5",
		"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 "RedHatAI/MiniMax-M2.5" \
        --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": "RedHatAI/MiniMax-M2.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

robgreenberg3 commited on 23 days ago

Commit

6baf9e4

verified ·

1 Parent(s): 3d3f94e

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -0

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ readme: https://huggingface.co/RedHatAI/MiniMax-M2.5/blob/main/README.md
 validated_on:
   - RHOAI 3.4 EA1
   - RHAIIS 3.4 EA1
 provider: MiniMax
 language:
 - en
@@ -103,6 +104,12 @@ M2.5 is the first frontier model where users do not need to worry about cost, de
 **ModelCar Storage URI:** oci://registry.redhat.io/rhai/modelcar-minimax-m2-5:3.0
 ## Coding
 In programming evaluations, MiniMax-M2.5 saw substantial improvements compared to previous generations, reaching SOTA levels. The performance of M2.5 in multilingual tasks is especially pronounced.

 validated_on:
   - RHOAI 3.4 EA1
   - RHAIIS 3.4 EA1
+  - vLLM 0.14.1
 provider: MiniMax
 language:
 - en
 **ModelCar Storage URI:** oci://registry.redhat.io/rhai/modelcar-minimax-m2-5:3.0
+**Validated on vLLM:** 0.14.1
+**Validated on RHAIIS:** 3.4 EA1
+**Validated on RHOAI:** 3.4 EA1
 ## Coding
 In programming evaluations, MiniMax-M2.5 saw substantial improvements compared to previous generations, reaching SOTA levels. The performance of M2.5 in multilingual tasks is especially pronounced.