Text Generation
Transformers
Safetensors
minimax_m2
neuralmagic
redhat
llmcompressor
quantized
FP4
conversational
custom_code
8-bit precision
compressed-tensors
Instructions to use RedHatAI/MiniMax-M2.5-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/MiniMax-M2.5-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RedHatAI/MiniMax-M2.5-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("RedHatAI/MiniMax-M2.5-NVFP4", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("RedHatAI/MiniMax-M2.5-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
- vLLM
How to use RedHatAI/MiniMax-M2.5-NVFP4 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-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": "RedHatAI/MiniMax-M2.5-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RedHatAI/MiniMax-M2.5-NVFP4
- SGLang
How to use RedHatAI/MiniMax-M2.5-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 "RedHatAI/MiniMax-M2.5-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": "RedHatAI/MiniMax-M2.5-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 "RedHatAI/MiniMax-M2.5-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": "RedHatAI/MiniMax-M2.5-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RedHatAI/MiniMax-M2.5-NVFP4 with Docker Model Runner:
docker model run hf.co/RedHatAI/MiniMax-M2.5-NVFP4
| { | |
| "schema_version": "0.2.2", | |
| "evaluation_id": "ifeval/RedHatAI/MiniMax-M2.5-NVFP4/1777381402.619951", | |
| "evaluation_timestamp": "1777304021", | |
| "retrieved_timestamp": "1777381402.619951", | |
| "source_metadata": { | |
| "source_name": "lm-evaluation-harness", | |
| "source_type": "evaluation_run", | |
| "source_organization_name": "RedHatAI", | |
| "evaluator_relationship": "third_party" | |
| }, | |
| "eval_library": { | |
| "name": "lm_eval", | |
| "version": "0.4.12.dev0" | |
| }, | |
| "model_info": { | |
| "name": "RedHatAI/MiniMax-M2.5-NVFP4", | |
| "id": "RedHatAI/MiniMax-M2.5-NVFP4", | |
| "developer": "RedHatAI", | |
| "additional_details": { | |
| "model_args": "{'model': 'RedHatAI/MiniMax-M2.5-NVFP4', 'max_length': 196608, 'base_url': 'http://0.0.0.0:8003/v1/chat/completions', 'num_concurrent': 128, 'max_retries': 3, 'tokenized_requests': False, 'tokenizer_backend': None, 'timeout': 2400}", | |
| "seed": "1234", | |
| "num_seeds_merged": "3" | |
| } | |
| }, | |
| "evaluation_results": [ | |
| { | |
| "evaluation_name": "ifeval", | |
| "source_data": { | |
| "dataset_name": "ifeval", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "google/IFEval", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "1777304940", | |
| "metric_config": { | |
| "evaluation_description": "prompt_level_strict_acc", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.8539741219963032, | |
| "details": { | |
| "seed_scores": "[0.8595194085027726, 0.8521256931608133, 0.8502772643253235]", | |
| "seed_values": "[1234, 4158, 42]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.0028235216851237458, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 3 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "until": "[]", | |
| "do_sample": "true", | |
| "min_p": "0.0", | |
| "presence_penalty": "1.5", | |
| "repetition_penalty": "1.0", | |
| "seed": "1234", | |
| "num_fewshot": "0" | |
| } | |
| } | |
| }, | |
| { | |
| "evaluation_name": "ifeval", | |
| "source_data": { | |
| "dataset_name": "ifeval", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "google/IFEval", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "1777304940", | |
| "metric_config": { | |
| "evaluation_description": "inst_level_strict_acc", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.898880895283773, | |
| "details": { | |
| "seed_scores": "[0.9052757793764988, 0.9004796163069544, 0.8908872901678657]", | |
| "seed_values": "[1234, 4158, 42]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.004229818243108859, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 3 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "until": "[]", | |
| "do_sample": "true", | |
| "min_p": "0.0", | |
| "presence_penalty": "1.5", | |
| "repetition_penalty": "1.0", | |
| "seed": "1234", | |
| "num_fewshot": "0" | |
| } | |
| } | |
| }, | |
| { | |
| "evaluation_name": "ifeval", | |
| "source_data": { | |
| "dataset_name": "ifeval", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "google/IFEval", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "1777304940", | |
| "metric_config": { | |
| "evaluation_description": "prompt_level_loose_acc", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.8829328404189772, | |
| "details": { | |
| "seed_scores": "[0.8964879852125693, 0.8743068391866913, 0.878003696857671]", | |
| "seed_values": "[1234, 4158, 42]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.006861077464978476, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 3 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "until": "[]", | |
| "do_sample": "true", | |
| "min_p": "0.0", | |
| "presence_penalty": "1.5", | |
| "repetition_penalty": "1.0", | |
| "seed": "1234", | |
| "num_fewshot": "0" | |
| } | |
| } | |
| }, | |
| { | |
| "evaluation_name": "ifeval", | |
| "source_data": { | |
| "dataset_name": "ifeval", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "google/IFEval", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "1777304940", | |
| "metric_config": { | |
| "evaluation_description": "inst_level_loose_acc", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.9180655475619505, | |
| "details": { | |
| "seed_scores": "[0.9292565947242206, 0.9148681055155875, 0.9100719424460432]", | |
| "seed_values": "[1234, 4158, 42]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.005764270624242989, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 3 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "until": "[]", | |
| "do_sample": "true", | |
| "min_p": "0.0", | |
| "presence_penalty": "1.5", | |
| "repetition_penalty": "1.0", | |
| "seed": "1234", | |
| "num_fewshot": "0" | |
| } | |
| } | |
| } | |
| ] | |
| } |