Instructions to use RedHatAI/MiniMax-M2.5-quantized.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/MiniMax-M2.5-quantized.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/MiniMax-M2.5-quantized.w8a8", 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-quantized.w8a8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("RedHatAI/MiniMax-M2.5-quantized.w8a8", 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-quantized.w8a8 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-quantized.w8a8"
# 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-quantized.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/MiniMax-M2.5-quantized.w8a8

SGLang

How to use RedHatAI/MiniMax-M2.5-quantized.w8a8 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-quantized.w8a8" \
    --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-quantized.w8a8",
		"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-quantized.w8a8" \
        --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-quantized.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/MiniMax-M2.5-quantized.w8a8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/MiniMax-M2.5-quantized.w8a8
```

Chibu Ukachi commited on 1 day ago

Commit

ee8242c

1 Parent(s): 79613cc

replace org name

Browse files

Files changed (6) hide show

every_eval_ever/aime25.json +4 -4
every_eval_ever/gpqa_diamond.json +4 -4
every_eval_ever/gsm8k_platinum_cot_llama.json +5 -5
every_eval_ever/ifeval.json +5 -5
every_eval_ever/math_500.json +4 -4
every_eval_ever/mmlu_pro_chat.json +5 -5

every_eval_ever/aime25.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "aime25/inference-optimization/MiniMax-M2.5.w8a8/1777568692.163912",
   "evaluation_timestamp": "7718166",
   "retrieved_timestamp": "1777568692.163912",
   "source_metadata": {
@@ -14,9 +14,9 @@
     "version": "v0.13.0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "inference_engine": {
       "name": "vllm"
     },

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "aime25/RedHatAI/MiniMax-M2.5.w8a8/1777568692.163912",
   "evaluation_timestamp": "7718166",
   "retrieved_timestamp": "1777568692.163912",
   "source_metadata": {
     "version": "v0.13.0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "inference_engine": {
       "name": "vllm"
     },

every_eval_ever/gpqa_diamond.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "gpqa:diamond/inference-optimization/MiniMax-M2.5.w8a8/1777568737.410978",
   "evaluation_timestamp": "7704068",
   "retrieved_timestamp": "1777568737.410978",
   "source_metadata": {
@@ -14,9 +14,9 @@
     "version": "v0.13.0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "inference_engine": {
       "name": "vllm"
     },

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "gpqa:diamond/RedHatAI/MiniMax-M2.5.w8a8/1777568737.410978",
   "evaluation_timestamp": "7704068",
   "retrieved_timestamp": "1777568737.410978",
   "source_metadata": {
     "version": "v0.13.0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "inference_engine": {
       "name": "vllm"
     },

every_eval_ever/gsm8k_platinum_cot_llama.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "gsm8k_platinum_cot_llama/inference-optimization/MiniMax-M2.5.w8a8/1777568615.837832",
   "evaluation_timestamp": "1777483916",
   "retrieved_timestamp": "1777568615.837832",
   "source_metadata": {
@@ -14,11 +14,11 @@
     "version": "0.4.12.dev0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "additional_details": {
-      "model_args": "{'model': 'inference-optimization/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "gsm8k_platinum_cot_llama/RedHatAI/MiniMax-M2.5.w8a8/1777568615.837832",
   "evaluation_timestamp": "1777483916",
   "retrieved_timestamp": "1777568615.837832",
   "source_metadata": {
     "version": "0.4.12.dev0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "additional_details": {
+      "model_args": "{'model': 'RedHatAI/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }

every_eval_ever/ifeval.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "ifeval/inference-optimization/MiniMax-M2.5.w8a8/1777568653.331068",
   "evaluation_timestamp": "1777485653",
   "retrieved_timestamp": "1777568653.331068",
   "source_metadata": {
@@ -14,11 +14,11 @@
     "version": "0.4.12.dev0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "additional_details": {
-      "model_args": "{'model': 'inference-optimization/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "ifeval/RedHatAI/MiniMax-M2.5.w8a8/1777568653.331068",
   "evaluation_timestamp": "1777485653",
   "retrieved_timestamp": "1777568653.331068",
   "source_metadata": {
     "version": "0.4.12.dev0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "additional_details": {
+      "model_args": "{'model': 'RedHatAI/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }

every_eval_ever/math_500.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "math_500/inference-optimization/MiniMax-M2.5.w8a8/1777568712.013831",
   "evaluation_timestamp": "7694693",
   "retrieved_timestamp": "1777568712.013831",
   "source_metadata": {
@@ -14,9 +14,9 @@
     "version": "v0.13.0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "inference_engine": {
       "name": "vllm"
     },

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "math_500/RedHatAI/MiniMax-M2.5.w8a8/1777568712.013831",
   "evaluation_timestamp": "7694693",
   "retrieved_timestamp": "1777568712.013831",
   "source_metadata": {
     "version": "v0.13.0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "inference_engine": {
       "name": "vllm"
     },

every_eval_ever/mmlu_pro_chat.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "schema_version": "0.2.2",
-  "evaluation_id": "mmlu_pro_chat/inference-optimization/MiniMax-M2.5.w8a8/1777980581.186022",
   "evaluation_timestamp": "1777572326",
   "retrieved_timestamp": "1777980581.186022",
   "source_metadata": {
@@ -14,11 +14,11 @@
     "version": "0.4.12.dev0"
   },
   "model_info": {
-    "name": "inference-optimization/MiniMax-M2.5.w8a8",
-    "id": "inference-optimization/MiniMax-M2.5.w8a8",
-    "developer": "inference-optimization",
     "additional_details": {
-      "model_args": "{'model': 'inference-optimization/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 28, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }

 {
   "schema_version": "0.2.2",
+  "evaluation_id": "mmlu_pro_chat/RedHatAI/MiniMax-M2.5.w8a8/1777980581.186022",
   "evaluation_timestamp": "1777572326",
   "retrieved_timestamp": "1777980581.186022",
   "source_metadata": {
     "version": "0.4.12.dev0"
   },
   "model_info": {
+    "name": "RedHatAI/MiniMax-M2.5.w8a8",
+    "id": "RedHatAI/MiniMax-M2.5.w8a8",
+    "developer": "RedHatAI",
     "additional_details": {
+      "model_args": "{'model': 'RedHatAI/MiniMax-M2.5.w8a8', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8000/v1/chat/completions', 'num_concurrent': 28, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}",
       "seed": "1234",
       "num_seeds_merged": "3"
     }