Instructions to use amd/MiniMax-M2.7-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/MiniMax-M2.7-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="amd/MiniMax-M2.7-MXFP4", 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-MXFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/MiniMax-M2.7-MXFP4", 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 amd/MiniMax-M2.7-MXFP4 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-MXFP4"
# 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-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/MiniMax-M2.7-MXFP4

SGLang

How to use amd/MiniMax-M2.7-MXFP4 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-MXFP4" \
    --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-MXFP4",
		"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-MXFP4" \
        --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-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/MiniMax-M2.7-MXFP4 with Docker Model Runner:
```
docker model run hf.co/amd/MiniMax-M2.7-MXFP4
```

haoyang-amd commited on Apr 24

Commit

69d9b02

verified ·

1 Parent(s): 9b118ac

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -8

README.md CHANGED Viewed

@@ -32,7 +32,6 @@ The model was quantized from [amd/MiniMax-M2.7-BF16](https://huggingface.co/amd/
 **Quantization scripts:**
 ```
 export exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
-export HIP_VISIBLE_DEVICES=4,5,6,7
 python3 quantize_quark.py --model_dir /shareddata/amd/MiniMax-M2.7-bf16 \
                           --quant_scheme mxfp4 \
                           --num_calib_data 128 \
@@ -66,11 +65,11 @@ The model was evaluated on gsm8k benchmarks using the vllm framework.
   <tr>
    <td>gsm8k (flexible-extract)
    </td>
-   <td>91.36
-   </td>
    <td>91.81
    </td>
-   <td>100.49%
    </td>
   </tr>
 </table>
@@ -84,15 +83,14 @@ The GSM8K results were obtained using the lm-eval framework, based on the Docker
 ```
 vllm serve "$MODEL" \
     --tensor-parallel-size 4 \
-    --trust-remote-code \
-    --max-model-len 32768 \
-    --port 8899
 ```
 #### Evaluating model in a new terminal
 ```
-python vllm/tests/evals/gsm8k/gsm8k_eval.py --host http://127.0.0.1 --port 8899
 ```

 **Quantization scripts:**
 ```
 export exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
 python3 quantize_quark.py --model_dir /shareddata/amd/MiniMax-M2.7-bf16 \
                           --quant_scheme mxfp4 \
                           --num_calib_data 128 \
   <tr>
    <td>gsm8k (flexible-extract)
    </td>
    <td>91.81
    </td>
+   <td>91.89
+   </td>
+   <td>100.09%
    </td>
   </tr>
 </table>
 ```
 vllm serve "$MODEL" \
     --tensor-parallel-size 4 \
+    --enable-auto-tool-choice --tool-call-parser minimax_m2 \
+    --reasoning-parser minimax_m2_append_think
 ```
 #### Evaluating model in a new terminal
 ```
+python vllm/tests/evals/gsm8k/gsm8k_eval.py
 ```