Instructions to use juspay/xor-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juspay/xor-nvfp4 with Transformers:

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

pipe = pipeline("text-generation", model="juspay/xor-nvfp4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("juspay/xor-nvfp4")
model = AutoModelForMultimodalLM.from_pretrained("juspay/xor-nvfp4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use juspay/xor-nvfp4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juspay/xor-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": "juspay/xor-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/juspay/xor-nvfp4

SGLang

How to use juspay/xor-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 "juspay/xor-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": "juspay/xor-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 "juspay/xor-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": "juspay/xor-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use juspay/xor-nvfp4 with Docker Model Runner:
```
docker model run hf.co/juspay/xor-nvfp4
```

xor-nvfp4 / hf_quant_config.json

pramodchandra

Add files using upload-large-folder tool

f02dbff verified 27 days ago

Raw History Blame Contribute Delete

3.51 kB

{
  "producer": {
    "name": "modelopt",
    "version": "0.44.0"
  },
  "quantization": {
    "quant_algo": "MIXED_PRECISION",
    "kv_cache_quant_algo": "FP8",
    "quantized_layers": {
      "model.language_model.layers.0.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.1.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.2.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.3.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.4.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.5.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.6.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.7.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.8.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.9.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.10.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.11.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.12.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.13.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.14.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.15.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.16.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.17.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.18.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.19.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.30.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.31.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.32.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.33.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.34.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      },
      "model.language_model.layers.35.mlp.experts": {
        "quant_algo": "W4A16_NVFP4",
        "group_size": 16
      }
    },
    "exclude_modules": [
      "mtp.layers.0*",
      "mtp*"
    ]
  }
}

	{
	"producer": {
	"name": "modelopt",
	"version": "0.44.0"
	},
	"quantization": {
	"quant_algo": "MIXED_PRECISION",
	"kv_cache_quant_algo": "FP8",
	"quantized_layers": {
	"model.language_model.layers.0.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.1.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.2.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.3.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.4.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.5.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.6.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.7.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.8.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.9.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.10.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.11.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.12.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.13.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.14.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.15.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.16.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.17.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.18.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.19.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.30.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.31.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.32.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.33.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.34.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	},
	"model.language_model.layers.35.mlp.experts": {
	"quant_algo": "W4A16_NVFP4",
	"group_size": 16
	}
	},
	"exclude_modules": [
	"mtp.layers.0*",
	"mtp*"
	]
	}
	}