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

Libraries

How to use QuantTrio/MiniMax-M2.7-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/MiniMax-M2.7-AWQ", 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("QuantTrio/MiniMax-M2.7-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("QuantTrio/MiniMax-M2.7-AWQ", 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 QuantTrio/MiniMax-M2.7-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/QuantTrio/MiniMax-M2.7-AWQ

SGLang

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

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

JunHowie commited on Apr 20

Commit

baecb18

verified ·

1 Parent(s): a3d0ac7

Add files using upload-large-folder tool

Browse files

Files changed (20) hide show

model-00002-of-00044.safetensors +3 -0
model-00007-of-00044.safetensors +3 -0
model-00013-of-00044.safetensors +3 -0
model-00014-of-00044.safetensors +3 -0
model-00016-of-00044.safetensors +3 -0
model-00018-of-00044.safetensors +3 -0
model-00021-of-00044.safetensors +3 -0
model-00022-of-00044.safetensors +3 -0
model-00027-of-00044.safetensors +3 -0
model-00028-of-00044.safetensors +3 -0
model-00029-of-00044.safetensors +3 -0
model-00032-of-00044.safetensors +3 -0
model-00033-of-00044.safetensors +3 -0
model-00034-of-00044.safetensors +3 -0
model-00035-of-00044.safetensors +3 -0
model-00036-of-00044.safetensors +3 -0
model-00038-of-00044.safetensors +3 -0
model-00041-of-00044.safetensors +3 -0
model-00043-of-00044.safetensors +3 -0
model-00044-of-00044.safetensors +3 -0

model-00002-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:29cc71da5d0aa5dcae2613a3b825b79a8235fed5fb8e54eef2b06e04e6a32f47
+size 2991628944

model-00007-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d082b15e4ac70d3650157ffaa9cc2906a35428f8146215c5db5e7e490a889cc3
+size 2999675224

model-00013-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:674eb50279c179aa08205f067ec8bab197282073f8b1ea2052ef7fc9a393b5cd
+size 2999678976

model-00014-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:66aba2b1d52a685f726b9435089b3632495b833341921822e684e1da8e06ae4a
+size 2999141880

model-00016-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:37cfddc105dd24495c227142693d36ef0b8657f4ad3358f0e5e0e4ecbde00276
+size 2993882864

model-00018-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4548df35420c3b415165cf6a2bdc75f47d451e0a41b3d8ba080c45220fb5b53
+size 2998289424

model-00021-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba3418e4e92d097be0c24e971f1c430881b8daae18dc677c1eeb85c0e0641c1
+size 2999142536

model-00022-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef85fb8205ed6e01a7dbfde4f05da57e6668efce750896854bff4935da18a538
+size 2999678408

model-00027-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3344a284e7410a4a77a1c038262852283b0c9573e42145f6c3c3ef15355bd317
+size 2999142488

model-00028-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:660e512e76aae2ea04527be3f294dc3e5d8ad70eee50ecd624b9b158b230e554
+size 2999678456

model-00029-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:21ee74f30f36fdb30675a3208e690517622e8e6d8b98fa04cbd0ebe1c80005bb
+size 2999142400

model-00032-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f98d2081cc73475c142e6948a592e9582008762db8a91599341896a0eb95dd
+size 2999678632

model-00033-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f848cf9a94012e6e72fcc0a17c449c256f1eeb5e351c851b9dd4bbf28bbc87
+size 2999142224

model-00034-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a67b813122be7929fe96acbed135c7534e391e386a70404dbef16ad1908f97c0
+size 2999678728

model-00035-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b56c3c9954882525bee658c5a8c341fe7e122ff3eb887fd5ce89c589c34587df
+size 2999142128

model-00036-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b02128352639c2caabcd6354183bff2b0ab51c7d6409dd9b0325cc7858a3d057
+size 2999678816

model-00038-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:019bd2734d71da5e3fa24822dd41db94813a939ced31692faa76e1085fcf9565
+size 2999678912

model-00041-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:51a6c39d96f9c9248180b0f3d06f94d4740c43be76bec0f65e87291667e79424
+size 2999141856

model-00043-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c6006e757af2bedf3cf355336ffd222258399d53357251c2068af478a54ef3
+size 2997318264

model-00044-of-00044.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:586a377a10e7193325387e4872d91a7628fec70420604a18e8528aeb74a54e33
+size 1273240008