Instructions to use saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="saricles/MiniMax-M2.7-REAP-172B-A10B-BF16", 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("saricles/MiniMax-M2.7-REAP-172B-A10B-BF16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("saricles/MiniMax-M2.7-REAP-172B-A10B-BF16", 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 saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saricles/MiniMax-M2.7-REAP-172B-A10B-BF16

SGLang

How to use saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 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 "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16" \
    --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": "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16",
		"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 "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16" \
        --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": "saricles/MiniMax-M2.7-REAP-172B-A10B-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 with Docker Model Runner:
```
docker model run hf.co/saricles/MiniMax-M2.7-REAP-172B-A10B-BF16
```

Pathname confusion

by catplusplus - opened 23 days ago

Discussion

catplusplus

23 days ago

So either there is some vLLM bug on my box (NVIDIA Thor) or MiniMax 2.5/2.7 REAPs prepared with stock calibration datasets can't handle Linux pathnames, like dropping a path component or changing case. Comparatively 3 bit GGUF seems to work fine (but is very slow vs NVFP4). Assuming others also see this, I wonder if calibration on a coding dataset for REAP would overcome this problem. Might get to trying this someday, need to figure out how to build a runpod docker container with things preinstalled, probably by testing locally on a smaller model. Among other things, how does one decompress MiniMax to BF16?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment