Instructions to use amd/MiniMax-M2.7-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/MiniMax-M2.7-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="amd/MiniMax-M2.7-NVFP4", 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("amd/MiniMax-M2.7-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/MiniMax-M2.7-NVFP4", 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 Settings

vLLM

How to use amd/MiniMax-M2.7-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/MiniMax-M2.7-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/MiniMax-M2.7-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/MiniMax-M2.7-NVFP4

SGLang

How to use amd/MiniMax-M2.7-NVFP4 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 "amd/MiniMax-M2.7-NVFP4" \
    --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": "amd/MiniMax-M2.7-NVFP4",
		"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 "amd/MiniMax-M2.7-NVFP4" \
        --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": "amd/MiniMax-M2.7-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/MiniMax-M2.7-NVFP4 with Docker Model Runner:
```
docker model run hf.co/amd/MiniMax-M2.7-NVFP4
```

update model card

by linzhao-amd - opened 3 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-4

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -15,23 +15,26 @@ license_link: https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE
   - **Output:** Text
 - **Supported Hardware Microarchitecture:** AMD MI300/MI350/MI355 (emulation)
 - **ROCm:** 7.2.2
 - **Operating System(s):** Linux
 - **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
 - **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (v0.12)
 - **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)
 - **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html)
   - **Weight quantization:** NVFP4, Static
   - **Activation quantization:** NVFP4, Dynamic
 # Model Quantization
-The model was quantized from [amd/MiniMax-M2.7-BF16](https://huggingface.co/amd/MiniMax-M2.7-BF16), originally from [MiniMax/MiniMax-M2.7](https://huggingface.co/MiniMax/MiniMax-M2.7), using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). The weights are quantized to NVFP4 and activations are quantized to NVFP4.
 **Quantization scripts:**
 ```
-cd /Quark/examples/torch/language_modeling/llm_ptq
 exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
 python3 quantize_quark.py --model_dir amd/MiniMax-M2.7-BF16 \
                           --quant_scheme nvfp4 \
@@ -45,8 +48,8 @@ python3 quantize_quark.py --model_dir amd/MiniMax-M2.7-BF16 \
 For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
-# Evaluation
 The model was evaluated on gsm8k benchmarks using the vllm framework.
 ### Accuracy

   - **Output:** Text
 - **Supported Hardware Microarchitecture:** AMD MI300/MI350/MI355 (emulation)
 - **ROCm:** 7.2.2
+- **PyTorch**: 2.10.0
+- **Transformers**: 5.2.0
 - **Operating System(s):** Linux
 - **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
 - **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (v0.12)
 - **Inference Engine:** [SGLang](https://docs.sglang.ai/)/[vLLM](https://docs.vllm.ai/en/latest/)
 - **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html)
+  - **Quantized layers:** `experts`
   - **Weight quantization:** NVFP4, Static
   - **Activation quantization:** NVFP4, Dynamic
 # Model Quantization
+The model was quantized from [amd/MiniMax-M2.7-BF16](https://huggingface.co/amd/MiniMax-M2.7-BF16), originally from [MiniMax/MiniMax-M2.7](https://huggingface.co/MiniMax/MiniMax-M2.7), using [AMD-Quark](https://quark.docs.amd.com/latest/index.html). The weights and activations are quantized to NVFP4.
 **Quantization scripts:**
 ```
+cd Quark/examples/torch/language_modeling/llm_ptq
 exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
 python3 quantize_quark.py --model_dir amd/MiniMax-M2.7-BF16 \
                           --quant_scheme nvfp4 \
 For further details or issues, please refer to the AMD-Quark documentation or contact the respective developers.
+# Deployment
+## Evaluation
 The model was evaluated on gsm8k benchmarks using the vllm framework.
 ### Accuracy