Instructions to use d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated with Transformers:

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

pipe = pipeline("image-text-to-text", model="d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated")
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("d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated")
model = AutoModelForMultimodalLM.from_pretrained("d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated", 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 d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated

SGLang

How to use d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated 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 "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated" \
    --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": "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated" \
        --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": "d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated with Docker Model Runner:
```
docker model run hf.co/d0xin/Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated
```

Swift-1.5-Qwen3.8-Flash-Next-NVFP4-FP8PLE-Rank2-Abliterated / hf_quant_config.json

d0xin

Upload full Flash-Next FP8PLE Rank-2 abliterated checkpoint

16b09a2 verified about 1 month ago

Raw History Blame Contribute Delete

20.5 kB

{
    "producer": {
        "name": "modelopt",
        "version": "0.47.0rc1.dev99+g7159c01d9"
    },
    "quantization": {
        "quant_algo": "NVFP4",
        "kv_cache_quant_algo": null,
        "group_size": 16,
        "exclude_modules": [
            "lm_head",
            "model.language_model.embed_tokens",
            "model.language_model.hyper_connection_mixer*",
            "model.language_model.layers.0.attn_hyper_connection*",
            "model.language_model.layers.0.linear_attn*",
            "model.language_model.layers.0.mlp.gate",
            "model.language_model.layers.0.mlp.shared_expert*",
            "model.language_model.layers.0.mlp.shared_expert_gate",
            "model.language_model.layers.0.mlp_hyper_connection*",
            "model.language_model.layers.1.attn_hyper_connection*",
            "model.language_model.layers.1.linear_attn*",
            "model.language_model.layers.1.mlp.gate",
            "model.language_model.layers.1.mlp.shared_expert*",
            "model.language_model.layers.1.mlp.shared_expert_gate",
            "model.language_model.layers.1.mlp_hyper_connection*",
            "model.language_model.layers.1.ple*",
            "model.language_model.layers.10.attn_hyper_connection*",
            "model.language_model.layers.10.linear_attn*",
            "model.language_model.layers.10.mlp.gate",
            "model.language_model.layers.10.mlp.shared_expert*",
            "model.language_model.layers.10.mlp.shared_expert_gate",
            "model.language_model.layers.10.mlp_hyper_connection*",
            "model.language_model.layers.11.attn_hyper_connection*",
            "model.language_model.layers.11.mlp.gate",
            "model.language_model.layers.11.mlp.shared_expert*",
            "model.language_model.layers.11.mlp.shared_expert_gate",
            "model.language_model.layers.11.mlp_hyper_connection*",
            "model.language_model.layers.11.self_attn*",
            "model.language_model.layers.12.attn_hyper_connection*",
            "model.language_model.layers.12.linear_attn*",
            "model.language_model.layers.12.mlp.gate",
            "model.language_model.layers.12.mlp.shared_expert*",
            "model.language_model.layers.12.mlp.shared_expert_gate",
            "model.language_model.layers.12.mlp_hyper_connection*",
            "model.language_model.layers.13.attn_hyper_connection*",
            "model.language_model.layers.13.linear_attn*",
            "model.language_model.layers.13.mlp.gate",
            "model.language_model.layers.13.mlp.shared_expert*",
            "model.language_model.layers.13.mlp.shared_expert_gate",
            "model.language_model.layers.13.mlp_hyper_connection*",
            "model.language_model.layers.14.attn_hyper_connection*",
            "model.language_model.layers.14.linear_attn*",
            "model.language_model.layers.14.mlp.gate",
            "model.language_model.layers.14.mlp.shared_expert*",
            "model.language_model.layers.14.mlp.shared_expert_gate",
            "model.language_model.layers.14.mlp_hyper_connection*",
            "model.language_model.layers.15.attn_hyper_connection*",
            "model.language_model.layers.15.mlp.gate",
            "model.language_model.layers.15.mlp.shared_expert*",
            "model.language_model.layers.15.mlp.shared_expert_gate",
            "model.language_model.layers.15.mlp_hyper_connection*",
            "model.language_model.layers.15.self_attn*",
            "model.language_model.layers.16.attn_hyper_connection*",
            "model.language_model.layers.16.linear_attn*",
            "model.language_model.layers.16.mlp.gate",
            "model.language_model.layers.16.mlp.shared_expert*",
            "model.language_model.layers.16.mlp.shared_expert_gate",
            "model.language_model.layers.16.mlp_hyper_connection*",
            "model.language_model.layers.17.attn_hyper_connection*",
            "model.language_model.layers.17.linear_attn*",
            "model.language_model.layers.17.mlp.gate",
            "model.language_model.layers.17.mlp.shared_expert*",
            "model.language_model.layers.17.mlp.shared_expert_gate",
            "model.language_model.layers.17.mlp_hyper_connection*",
            "model.language_model.layers.18.attn_hyper_connection*",
            "model.language_model.layers.18.linear_attn*",
            "model.language_model.layers.18.mlp.gate",
            "model.language_model.layers.18.mlp.shared_expert*",
            "model.language_model.layers.18.mlp.shared_expert_gate",
            "model.language_model.layers.18.mlp_hyper_connection*",
            "model.language_model.layers.19.attn_hyper_connection*",
            "model.language_model.layers.19.mlp.gate",
            "model.language_model.layers.19.mlp.shared_expert*",
            "model.language_model.layers.19.mlp.shared_expert_gate",
            "model.language_model.layers.19.mlp_hyper_connection*",
            "model.language_model.layers.19.self_attn*",
            "model.language_model.layers.2.attn_hyper_connection*",
            "model.language_model.layers.2.linear_attn*",
            "model.language_model.layers.2.mlp.gate",
            "model.language_model.layers.2.mlp.shared_expert*",
            "model.language_model.layers.2.mlp.shared_expert_gate",
            "model.language_model.layers.2.mlp_hyper_connection*",
            "model.language_model.layers.20.attn_hyper_connection*",
            "model.language_model.layers.20.linear_attn*",
            "model.language_model.layers.20.mlp.gate",
            "model.language_model.layers.20.mlp.shared_expert*",
            "model.language_model.layers.20.mlp.shared_expert_gate",
            "model.language_model.layers.20.mlp_hyper_connection*",
            "model.language_model.layers.21.attn_hyper_connection*",
            "model.language_model.layers.21.linear_attn*",
            "model.language_model.layers.21.mlp.gate",
            "model.language_model.layers.21.mlp.shared_expert*",
            "model.language_model.layers.21.mlp.shared_expert_gate",
            "model.language_model.layers.21.mlp_hyper_connection*",
            "model.language_model.layers.22.attn_hyper_connection*",
            "model.language_model.layers.22.linear_attn*",
            "model.language_model.layers.22.mlp.gate",
            "model.language_model.layers.22.mlp.shared_expert*",
            "model.language_model.layers.22.mlp.shared_expert_gate",
            "model.language_model.layers.22.mlp_hyper_connection*",
            "model.language_model.layers.23.attn_hyper_connection*",
            "model.language_model.layers.23.mlp.gate",
            "model.language_model.layers.23.mlp.shared_expert*",
            "model.language_model.layers.23.mlp.shared_expert_gate",
            "model.language_model.layers.23.mlp_hyper_connection*",
            "model.language_model.layers.23.self_attn*",
            "model.language_model.layers.24.attn_hyper_connection*",
            "model.language_model.layers.24.linear_attn*",
            "model.language_model.layers.24.mlp.gate",
            "model.language_model.layers.24.mlp.shared_expert*",
            "model.language_model.layers.24.mlp.shared_expert_gate",
            "model.language_model.layers.24.mlp_hyper_connection*",
            "model.language_model.layers.25.attn_hyper_connection*",
            "model.language_model.layers.25.linear_attn*",
            "model.language_model.layers.25.mlp.gate",
            "model.language_model.layers.25.mlp.shared_expert*",
            "model.language_model.layers.25.mlp.shared_expert_gate",
            "model.language_model.layers.25.mlp_hyper_connection*",
            "model.language_model.layers.26.attn_hyper_connection*",
            "model.language_model.layers.26.linear_attn*",
            "model.language_model.layers.26.mlp.gate",
            "model.language_model.layers.26.mlp.shared_expert*",
            "model.language_model.layers.26.mlp.shared_expert_gate",
            "model.language_model.layers.26.mlp_hyper_connection*",
            "model.language_model.layers.27.attn_hyper_connection*",
            "model.language_model.layers.27.mlp.gate",
            "model.language_model.layers.27.mlp.shared_expert*",
            "model.language_model.layers.27.mlp.shared_expert_gate",
            "model.language_model.layers.27.mlp_hyper_connection*",
            "model.language_model.layers.27.self_attn*",
            "model.language_model.layers.28.attn_hyper_connection*",
            "model.language_model.layers.28.linear_attn*",
            "model.language_model.layers.28.mlp.gate",
            "model.language_model.layers.28.mlp.shared_expert*",
            "model.language_model.layers.28.mlp.shared_expert_gate",
            "model.language_model.layers.28.mlp_hyper_connection*",
            "model.language_model.layers.29.attn_hyper_connection*",
            "model.language_model.layers.29.linear_attn*",
            "model.language_model.layers.29.mlp.gate",
            "model.language_model.layers.29.mlp.shared_expert*",
            "model.language_model.layers.29.mlp.shared_expert_gate",
            "model.language_model.layers.29.mlp_hyper_connection*",
            "model.language_model.layers.3.attn_hyper_connection*",
            "model.language_model.layers.3.mlp.gate",
            "model.language_model.layers.3.mlp.shared_expert*",
            "model.language_model.layers.3.mlp.shared_expert_gate",
            "model.language_model.layers.3.mlp_hyper_connection*",
            "model.language_model.layers.3.self_attn*",
            "model.language_model.layers.30.attn_hyper_connection*",
            "model.language_model.layers.30.linear_attn*",
            "model.language_model.layers.30.mlp.gate",
            "model.language_model.layers.30.mlp.shared_expert*",
            "model.language_model.layers.30.mlp.shared_expert_gate",
            "model.language_model.layers.30.mlp_hyper_connection*",
            "model.language_model.layers.31.attn_hyper_connection*",
            "model.language_model.layers.31.mlp.gate",
            "model.language_model.layers.31.mlp.shared_expert*",
            "model.language_model.layers.31.mlp.shared_expert_gate",
            "model.language_model.layers.31.mlp_hyper_connection*",
            "model.language_model.layers.31.self_attn*",
            "model.language_model.layers.32.attn_hyper_connection*",
            "model.language_model.layers.32.linear_attn*",
            "model.language_model.layers.32.mlp.gate",
            "model.language_model.layers.32.mlp.shared_expert*",
            "model.language_model.layers.32.mlp.shared_expert_gate",
            "model.language_model.layers.32.mlp_hyper_connection*",
            "model.language_model.layers.33.attn_hyper_connection*",
            "model.language_model.layers.33.linear_attn*",
            "model.language_model.layers.33.mlp.gate",
            "model.language_model.layers.33.mlp.shared_expert*",
            "model.language_model.layers.33.mlp.shared_expert_gate",
            "model.language_model.layers.33.mlp_hyper_connection*",
            "model.language_model.layers.34.attn_hyper_connection*",
            "model.language_model.layers.34.linear_attn*",
            "model.language_model.layers.34.mlp.gate",
            "model.language_model.layers.34.mlp.shared_expert*",
            "model.language_model.layers.34.mlp.shared_expert_gate",
            "model.language_model.layers.34.mlp_hyper_connection*",
            "model.language_model.layers.35.attn_hyper_connection*",
            "model.language_model.layers.35.mlp.gate",
            "model.language_model.layers.35.mlp.shared_expert*",
            "model.language_model.layers.35.mlp.shared_expert_gate",
            "model.language_model.layers.35.mlp_hyper_connection*",
            "model.language_model.layers.35.self_attn*",
            "model.language_model.layers.36.attn_hyper_connection*",
            "model.language_model.layers.36.linear_attn*",
            "model.language_model.layers.36.mlp.gate",
            "model.language_model.layers.36.mlp.shared_expert*",
            "model.language_model.layers.36.mlp.shared_expert_gate",
            "model.language_model.layers.36.mlp_hyper_connection*",
            "model.language_model.layers.37.attn_hyper_connection*",
            "model.language_model.layers.37.linear_attn*",
            "model.language_model.layers.37.mlp.gate",
            "model.language_model.layers.37.mlp.shared_expert*",
            "model.language_model.layers.37.mlp.shared_expert_gate",
            "model.language_model.layers.37.mlp_hyper_connection*",
            "model.language_model.layers.38.attn_hyper_connection*",
            "model.language_model.layers.38.linear_attn*",
            "model.language_model.layers.38.mlp.gate",
            "model.language_model.layers.38.mlp.shared_expert*",
            "model.language_model.layers.38.mlp.shared_expert_gate",
            "model.language_model.layers.38.mlp_hyper_connection*",
            "model.language_model.layers.39.attn_hyper_connection*",
            "model.language_model.layers.39.mlp.gate",
            "model.language_model.layers.39.mlp.shared_expert*",
            "model.language_model.layers.39.mlp.shared_expert_gate",
            "model.language_model.layers.39.mlp_hyper_connection*",
            "model.language_model.layers.39.self_attn*",
            "model.language_model.layers.4.attn_hyper_connection*",
            "model.language_model.layers.4.linear_attn*",
            "model.language_model.layers.4.mlp.gate",
            "model.language_model.layers.4.mlp.shared_expert*",
            "model.language_model.layers.4.mlp.shared_expert_gate",
            "model.language_model.layers.4.mlp_hyper_connection*",
            "model.language_model.layers.40.attn_hyper_connection*",
            "model.language_model.layers.40.linear_attn*",
            "model.language_model.layers.40.mlp.gate",
            "model.language_model.layers.40.mlp.shared_expert*",
            "model.language_model.layers.40.mlp.shared_expert_gate",
            "model.language_model.layers.40.mlp_hyper_connection*",
            "model.language_model.layers.41.attn_hyper_connection*",
            "model.language_model.layers.41.linear_attn*",
            "model.language_model.layers.41.mlp.gate",
            "model.language_model.layers.41.mlp.shared_expert*",
            "model.language_model.layers.41.mlp.shared_expert_gate",
            "model.language_model.layers.41.mlp_hyper_connection*",
            "model.language_model.layers.42.attn_hyper_connection*",
            "model.language_model.layers.42.linear_attn*",
            "model.language_model.layers.42.mlp.gate",
            "model.language_model.layers.42.mlp.shared_expert*",
            "model.language_model.layers.42.mlp.shared_expert_gate",
            "model.language_model.layers.42.mlp_hyper_connection*",
            "model.language_model.layers.43.attn_hyper_connection*",
            "model.language_model.layers.43.mlp.gate",
            "model.language_model.layers.43.mlp.shared_expert*",
            "model.language_model.layers.43.mlp.shared_expert_gate",
            "model.language_model.layers.43.mlp_hyper_connection*",
            "model.language_model.layers.43.self_attn*",
            "model.language_model.layers.44.attn_hyper_connection*",
            "model.language_model.layers.44.linear_attn*",
            "model.language_model.layers.44.mlp.gate",
            "model.language_model.layers.44.mlp.shared_expert*",
            "model.language_model.layers.44.mlp.shared_expert_gate",
            "model.language_model.layers.44.mlp_hyper_connection*",
            "model.language_model.layers.45.attn_hyper_connection*",
            "model.language_model.layers.45.linear_attn*",
            "model.language_model.layers.45.mlp.gate",
            "model.language_model.layers.45.mlp.shared_expert*",
            "model.language_model.layers.45.mlp.shared_expert_gate",
            "model.language_model.layers.45.mlp_hyper_connection*",
            "model.language_model.layers.46.attn_hyper_connection*",
            "model.language_model.layers.46.linear_attn*",
            "model.language_model.layers.46.mlp.gate",
            "model.language_model.layers.46.mlp.shared_expert*",
            "model.language_model.layers.46.mlp.shared_expert_gate",
            "model.language_model.layers.46.mlp_hyper_connection*",
            "model.language_model.layers.47.attn_hyper_connection*",
            "model.language_model.layers.47.mlp.gate",
            "model.language_model.layers.47.mlp.shared_expert*",
            "model.language_model.layers.47.mlp.shared_expert_gate",
            "model.language_model.layers.47.mlp_hyper_connection*",
            "model.language_model.layers.47.self_attn*",
            "model.language_model.layers.5.attn_hyper_connection*",
            "model.language_model.layers.5.linear_attn*",
            "model.language_model.layers.5.mlp.gate",
            "model.language_model.layers.5.mlp.shared_expert*",
            "model.language_model.layers.5.mlp.shared_expert_gate",
            "model.language_model.layers.5.mlp_hyper_connection*",
            "model.language_model.layers.6.attn_hyper_connection*",
            "model.language_model.layers.6.linear_attn*",
            "model.language_model.layers.6.mlp.gate",
            "model.language_model.layers.6.mlp.shared_expert*",
            "model.language_model.layers.6.mlp.shared_expert_gate",
            "model.language_model.layers.6.mlp_hyper_connection*",
            "model.language_model.layers.7.attn_hyper_connection*",
            "model.language_model.layers.7.mlp.gate",
            "model.language_model.layers.7.mlp.shared_expert*",
            "model.language_model.layers.7.mlp.shared_expert_gate",
            "model.language_model.layers.7.mlp_hyper_connection*",
            "model.language_model.layers.7.self_attn*",
            "model.language_model.layers.8.attn_hyper_connection*",
            "model.language_model.layers.8.linear_attn*",
            "model.language_model.layers.8.mlp.gate",
            "model.language_model.layers.8.mlp.shared_expert*",
            "model.language_model.layers.8.mlp.shared_expert_gate",
            "model.language_model.layers.8.mlp_hyper_connection*",
            "model.language_model.layers.9.attn_hyper_connection*",
            "model.language_model.layers.9.linear_attn*",
            "model.language_model.layers.9.mlp.gate",
            "model.language_model.layers.9.mlp.shared_expert*",
            "model.language_model.layers.9.mlp.shared_expert_gate",
            "model.language_model.layers.9.mlp_hyper_connection*",
            "model.visual*",
            "mtp.fc_embedding",
            "mtp.fc_hidden",
            "mtp.hyper_connection_mixer.hc_norm",
            "mtp.hyper_connection_mixer.input_mix_weight_down",
            "mtp.hyper_connection_mixer.input_mix_weight_up",
            "mtp.layers.0.attn_hyper_connection.block_inject_weight",
            "mtp.layers.0.attn_hyper_connection.hc_norm",
            "mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
            "mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
            "mtp.layers.0.mlp.experts",
            "mtp.layers.0.mlp.gate",
            "mtp.layers.0.mlp.shared_expert.down_proj",
            "mtp.layers.0.mlp.shared_expert.gate_proj",
            "mtp.layers.0.mlp.shared_expert.up_proj",
            "mtp.layers.0.mlp.shared_expert_gate",
            "mtp.layers.0.mlp_hyper_connection.block_inject_weight",
            "mtp.layers.0.mlp_hyper_connection.hc_norm",
            "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
            "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
            "mtp.layers.0.self_attn.indexer.index_qk_proj",
            "mtp.layers.0.self_attn.indexer.k_layernorm",
            "mtp.layers.0.self_attn.indexer.q_layernorm",
            "mtp.layers.0.self_attn.k_norm",
            "mtp.layers.0.self_attn.k_proj",
            "mtp.layers.0.self_attn.o_proj",
            "mtp.layers.0.self_attn.q_norm",
            "mtp.layers.0.self_attn.q_proj",
            "mtp.layers.0.self_attn.v_proj",
            "mtp.pre_fc_norm_embedding",
            "mtp.pre_fc_norm_hidden"
        ]
    }
}

	{
	"producer": {
	"name": "modelopt",
	"version": "0.47.0rc1.dev99+g7159c01d9"
	},
	"quantization": {
	"quant_algo": "NVFP4",
	"kv_cache_quant_algo": null,
	"group_size": 16,
	"exclude_modules": [
	"lm_head",
	"model.language_model.embed_tokens",
	"model.language_model.hyper_connection_mixer*",
	"model.language_model.layers.0.attn_hyper_connection*",
	"model.language_model.layers.0.linear_attn*",
	"model.language_model.layers.0.mlp.gate",
	"model.language_model.layers.0.mlp.shared_expert*",
	"model.language_model.layers.0.mlp.shared_expert_gate",
	"model.language_model.layers.0.mlp_hyper_connection*",
	"model.language_model.layers.1.attn_hyper_connection*",
	"model.language_model.layers.1.linear_attn*",
	"model.language_model.layers.1.mlp.gate",
	"model.language_model.layers.1.mlp.shared_expert*",
	"model.language_model.layers.1.mlp.shared_expert_gate",
	"model.language_model.layers.1.mlp_hyper_connection*",
	"model.language_model.layers.1.ple*",
	"model.language_model.layers.10.attn_hyper_connection*",
	"model.language_model.layers.10.linear_attn*",
	"model.language_model.layers.10.mlp.gate",
	"model.language_model.layers.10.mlp.shared_expert*",
	"model.language_model.layers.10.mlp.shared_expert_gate",
	"model.language_model.layers.10.mlp_hyper_connection*",
	"model.language_model.layers.11.attn_hyper_connection*",
	"model.language_model.layers.11.mlp.gate",
	"model.language_model.layers.11.mlp.shared_expert*",
	"model.language_model.layers.11.mlp.shared_expert_gate",
	"model.language_model.layers.11.mlp_hyper_connection*",
	"model.language_model.layers.11.self_attn*",
	"model.language_model.layers.12.attn_hyper_connection*",
	"model.language_model.layers.12.linear_attn*",
	"model.language_model.layers.12.mlp.gate",
	"model.language_model.layers.12.mlp.shared_expert*",
	"model.language_model.layers.12.mlp.shared_expert_gate",
	"model.language_model.layers.12.mlp_hyper_connection*",
	"model.language_model.layers.13.attn_hyper_connection*",
	"model.language_model.layers.13.linear_attn*",
	"model.language_model.layers.13.mlp.gate",
	"model.language_model.layers.13.mlp.shared_expert*",
	"model.language_model.layers.13.mlp.shared_expert_gate",
	"model.language_model.layers.13.mlp_hyper_connection*",
	"model.language_model.layers.14.attn_hyper_connection*",
	"model.language_model.layers.14.linear_attn*",
	"model.language_model.layers.14.mlp.gate",
	"model.language_model.layers.14.mlp.shared_expert*",
	"model.language_model.layers.14.mlp.shared_expert_gate",
	"model.language_model.layers.14.mlp_hyper_connection*",
	"model.language_model.layers.15.attn_hyper_connection*",
	"model.language_model.layers.15.mlp.gate",
	"model.language_model.layers.15.mlp.shared_expert*",
	"model.language_model.layers.15.mlp.shared_expert_gate",
	"model.language_model.layers.15.mlp_hyper_connection*",
	"model.language_model.layers.15.self_attn*",
	"model.language_model.layers.16.attn_hyper_connection*",
	"model.language_model.layers.16.linear_attn*",
	"model.language_model.layers.16.mlp.gate",
	"model.language_model.layers.16.mlp.shared_expert*",
	"model.language_model.layers.16.mlp.shared_expert_gate",
	"model.language_model.layers.16.mlp_hyper_connection*",
	"model.language_model.layers.17.attn_hyper_connection*",
	"model.language_model.layers.17.linear_attn*",
	"model.language_model.layers.17.mlp.gate",
	"model.language_model.layers.17.mlp.shared_expert*",
	"model.language_model.layers.17.mlp.shared_expert_gate",
	"model.language_model.layers.17.mlp_hyper_connection*",
	"model.language_model.layers.18.attn_hyper_connection*",
	"model.language_model.layers.18.linear_attn*",
	"model.language_model.layers.18.mlp.gate",
	"model.language_model.layers.18.mlp.shared_expert*",
	"model.language_model.layers.18.mlp.shared_expert_gate",
	"model.language_model.layers.18.mlp_hyper_connection*",
	"model.language_model.layers.19.attn_hyper_connection*",
	"model.language_model.layers.19.mlp.gate",
	"model.language_model.layers.19.mlp.shared_expert*",
	"model.language_model.layers.19.mlp.shared_expert_gate",
	"model.language_model.layers.19.mlp_hyper_connection*",
	"model.language_model.layers.19.self_attn*",
	"model.language_model.layers.2.attn_hyper_connection*",
	"model.language_model.layers.2.linear_attn*",
	"model.language_model.layers.2.mlp.gate",
	"model.language_model.layers.2.mlp.shared_expert*",
	"model.language_model.layers.2.mlp.shared_expert_gate",
	"model.language_model.layers.2.mlp_hyper_connection*",
	"model.language_model.layers.20.attn_hyper_connection*",
	"model.language_model.layers.20.linear_attn*",
	"model.language_model.layers.20.mlp.gate",
	"model.language_model.layers.20.mlp.shared_expert*",
	"model.language_model.layers.20.mlp.shared_expert_gate",
	"model.language_model.layers.20.mlp_hyper_connection*",
	"model.language_model.layers.21.attn_hyper_connection*",
	"model.language_model.layers.21.linear_attn*",
	"model.language_model.layers.21.mlp.gate",
	"model.language_model.layers.21.mlp.shared_expert*",
	"model.language_model.layers.21.mlp.shared_expert_gate",
	"model.language_model.layers.21.mlp_hyper_connection*",
	"model.language_model.layers.22.attn_hyper_connection*",
	"model.language_model.layers.22.linear_attn*",
	"model.language_model.layers.22.mlp.gate",
	"model.language_model.layers.22.mlp.shared_expert*",
	"model.language_model.layers.22.mlp.shared_expert_gate",
	"model.language_model.layers.22.mlp_hyper_connection*",
	"model.language_model.layers.23.attn_hyper_connection*",
	"model.language_model.layers.23.mlp.gate",
	"model.language_model.layers.23.mlp.shared_expert*",
	"model.language_model.layers.23.mlp.shared_expert_gate",
	"model.language_model.layers.23.mlp_hyper_connection*",
	"model.language_model.layers.23.self_attn*",
	"model.language_model.layers.24.attn_hyper_connection*",
	"model.language_model.layers.24.linear_attn*",
	"model.language_model.layers.24.mlp.gate",
	"model.language_model.layers.24.mlp.shared_expert*",
	"model.language_model.layers.24.mlp.shared_expert_gate",
	"model.language_model.layers.24.mlp_hyper_connection*",
	"model.language_model.layers.25.attn_hyper_connection*",
	"model.language_model.layers.25.linear_attn*",
	"model.language_model.layers.25.mlp.gate",
	"model.language_model.layers.25.mlp.shared_expert*",
	"model.language_model.layers.25.mlp.shared_expert_gate",
	"model.language_model.layers.25.mlp_hyper_connection*",
	"model.language_model.layers.26.attn_hyper_connection*",
	"model.language_model.layers.26.linear_attn*",
	"model.language_model.layers.26.mlp.gate",
	"model.language_model.layers.26.mlp.shared_expert*",
	"model.language_model.layers.26.mlp.shared_expert_gate",
	"model.language_model.layers.26.mlp_hyper_connection*",
	"model.language_model.layers.27.attn_hyper_connection*",
	"model.language_model.layers.27.mlp.gate",
	"model.language_model.layers.27.mlp.shared_expert*",
	"model.language_model.layers.27.mlp.shared_expert_gate",
	"model.language_model.layers.27.mlp_hyper_connection*",
	"model.language_model.layers.27.self_attn*",
	"model.language_model.layers.28.attn_hyper_connection*",
	"model.language_model.layers.28.linear_attn*",
	"model.language_model.layers.28.mlp.gate",
	"model.language_model.layers.28.mlp.shared_expert*",
	"model.language_model.layers.28.mlp.shared_expert_gate",
	"model.language_model.layers.28.mlp_hyper_connection*",
	"model.language_model.layers.29.attn_hyper_connection*",
	"model.language_model.layers.29.linear_attn*",
	"model.language_model.layers.29.mlp.gate",
	"model.language_model.layers.29.mlp.shared_expert*",
	"model.language_model.layers.29.mlp.shared_expert_gate",
	"model.language_model.layers.29.mlp_hyper_connection*",
	"model.language_model.layers.3.attn_hyper_connection*",
	"model.language_model.layers.3.mlp.gate",
	"model.language_model.layers.3.mlp.shared_expert*",
	"model.language_model.layers.3.mlp.shared_expert_gate",
	"model.language_model.layers.3.mlp_hyper_connection*",
	"model.language_model.layers.3.self_attn*",
	"model.language_model.layers.30.attn_hyper_connection*",
	"model.language_model.layers.30.linear_attn*",
	"model.language_model.layers.30.mlp.gate",
	"model.language_model.layers.30.mlp.shared_expert*",
	"model.language_model.layers.30.mlp.shared_expert_gate",
	"model.language_model.layers.30.mlp_hyper_connection*",
	"model.language_model.layers.31.attn_hyper_connection*",
	"model.language_model.layers.31.mlp.gate",
	"model.language_model.layers.31.mlp.shared_expert*",
	"model.language_model.layers.31.mlp.shared_expert_gate",
	"model.language_model.layers.31.mlp_hyper_connection*",
	"model.language_model.layers.31.self_attn*",
	"model.language_model.layers.32.attn_hyper_connection*",
	"model.language_model.layers.32.linear_attn*",
	"model.language_model.layers.32.mlp.gate",
	"model.language_model.layers.32.mlp.shared_expert*",
	"model.language_model.layers.32.mlp.shared_expert_gate",
	"model.language_model.layers.32.mlp_hyper_connection*",
	"model.language_model.layers.33.attn_hyper_connection*",
	"model.language_model.layers.33.linear_attn*",
	"model.language_model.layers.33.mlp.gate",
	"model.language_model.layers.33.mlp.shared_expert*",
	"model.language_model.layers.33.mlp.shared_expert_gate",
	"model.language_model.layers.33.mlp_hyper_connection*",
	"model.language_model.layers.34.attn_hyper_connection*",
	"model.language_model.layers.34.linear_attn*",
	"model.language_model.layers.34.mlp.gate",
	"model.language_model.layers.34.mlp.shared_expert*",
	"model.language_model.layers.34.mlp.shared_expert_gate",
	"model.language_model.layers.34.mlp_hyper_connection*",
	"model.language_model.layers.35.attn_hyper_connection*",
	"model.language_model.layers.35.mlp.gate",
	"model.language_model.layers.35.mlp.shared_expert*",
	"model.language_model.layers.35.mlp.shared_expert_gate",
	"model.language_model.layers.35.mlp_hyper_connection*",
	"model.language_model.layers.35.self_attn*",
	"model.language_model.layers.36.attn_hyper_connection*",
	"model.language_model.layers.36.linear_attn*",
	"model.language_model.layers.36.mlp.gate",
	"model.language_model.layers.36.mlp.shared_expert*",
	"model.language_model.layers.36.mlp.shared_expert_gate",
	"model.language_model.layers.36.mlp_hyper_connection*",
	"model.language_model.layers.37.attn_hyper_connection*",
	"model.language_model.layers.37.linear_attn*",
	"model.language_model.layers.37.mlp.gate",
	"model.language_model.layers.37.mlp.shared_expert*",
	"model.language_model.layers.37.mlp.shared_expert_gate",
	"model.language_model.layers.37.mlp_hyper_connection*",
	"model.language_model.layers.38.attn_hyper_connection*",
	"model.language_model.layers.38.linear_attn*",
	"model.language_model.layers.38.mlp.gate",
	"model.language_model.layers.38.mlp.shared_expert*",
	"model.language_model.layers.38.mlp.shared_expert_gate",
	"model.language_model.layers.38.mlp_hyper_connection*",
	"model.language_model.layers.39.attn_hyper_connection*",
	"model.language_model.layers.39.mlp.gate",
	"model.language_model.layers.39.mlp.shared_expert*",
	"model.language_model.layers.39.mlp.shared_expert_gate",
	"model.language_model.layers.39.mlp_hyper_connection*",
	"model.language_model.layers.39.self_attn*",
	"model.language_model.layers.4.attn_hyper_connection*",
	"model.language_model.layers.4.linear_attn*",
	"model.language_model.layers.4.mlp.gate",
	"model.language_model.layers.4.mlp.shared_expert*",
	"model.language_model.layers.4.mlp.shared_expert_gate",
	"model.language_model.layers.4.mlp_hyper_connection*",
	"model.language_model.layers.40.attn_hyper_connection*",
	"model.language_model.layers.40.linear_attn*",
	"model.language_model.layers.40.mlp.gate",
	"model.language_model.layers.40.mlp.shared_expert*",
	"model.language_model.layers.40.mlp.shared_expert_gate",
	"model.language_model.layers.40.mlp_hyper_connection*",
	"model.language_model.layers.41.attn_hyper_connection*",
	"model.language_model.layers.41.linear_attn*",
	"model.language_model.layers.41.mlp.gate",
	"model.language_model.layers.41.mlp.shared_expert*",
	"model.language_model.layers.41.mlp.shared_expert_gate",
	"model.language_model.layers.41.mlp_hyper_connection*",
	"model.language_model.layers.42.attn_hyper_connection*",
	"model.language_model.layers.42.linear_attn*",
	"model.language_model.layers.42.mlp.gate",
	"model.language_model.layers.42.mlp.shared_expert*",
	"model.language_model.layers.42.mlp.shared_expert_gate",
	"model.language_model.layers.42.mlp_hyper_connection*",
	"model.language_model.layers.43.attn_hyper_connection*",
	"model.language_model.layers.43.mlp.gate",
	"model.language_model.layers.43.mlp.shared_expert*",
	"model.language_model.layers.43.mlp.shared_expert_gate",
	"model.language_model.layers.43.mlp_hyper_connection*",
	"model.language_model.layers.43.self_attn*",
	"model.language_model.layers.44.attn_hyper_connection*",
	"model.language_model.layers.44.linear_attn*",
	"model.language_model.layers.44.mlp.gate",
	"model.language_model.layers.44.mlp.shared_expert*",
	"model.language_model.layers.44.mlp.shared_expert_gate",
	"model.language_model.layers.44.mlp_hyper_connection*",
	"model.language_model.layers.45.attn_hyper_connection*",
	"model.language_model.layers.45.linear_attn*",
	"model.language_model.layers.45.mlp.gate",
	"model.language_model.layers.45.mlp.shared_expert*",
	"model.language_model.layers.45.mlp.shared_expert_gate",
	"model.language_model.layers.45.mlp_hyper_connection*",
	"model.language_model.layers.46.attn_hyper_connection*",
	"model.language_model.layers.46.linear_attn*",
	"model.language_model.layers.46.mlp.gate",
	"model.language_model.layers.46.mlp.shared_expert*",
	"model.language_model.layers.46.mlp.shared_expert_gate",
	"model.language_model.layers.46.mlp_hyper_connection*",
	"model.language_model.layers.47.attn_hyper_connection*",
	"model.language_model.layers.47.mlp.gate",
	"model.language_model.layers.47.mlp.shared_expert*",
	"model.language_model.layers.47.mlp.shared_expert_gate",
	"model.language_model.layers.47.mlp_hyper_connection*",
	"model.language_model.layers.47.self_attn*",
	"model.language_model.layers.5.attn_hyper_connection*",
	"model.language_model.layers.5.linear_attn*",
	"model.language_model.layers.5.mlp.gate",
	"model.language_model.layers.5.mlp.shared_expert*",
	"model.language_model.layers.5.mlp.shared_expert_gate",
	"model.language_model.layers.5.mlp_hyper_connection*",
	"model.language_model.layers.6.attn_hyper_connection*",
	"model.language_model.layers.6.linear_attn*",
	"model.language_model.layers.6.mlp.gate",
	"model.language_model.layers.6.mlp.shared_expert*",
	"model.language_model.layers.6.mlp.shared_expert_gate",
	"model.language_model.layers.6.mlp_hyper_connection*",
	"model.language_model.layers.7.attn_hyper_connection*",
	"model.language_model.layers.7.mlp.gate",
	"model.language_model.layers.7.mlp.shared_expert*",
	"model.language_model.layers.7.mlp.shared_expert_gate",
	"model.language_model.layers.7.mlp_hyper_connection*",
	"model.language_model.layers.7.self_attn*",
	"model.language_model.layers.8.attn_hyper_connection*",
	"model.language_model.layers.8.linear_attn*",
	"model.language_model.layers.8.mlp.gate",
	"model.language_model.layers.8.mlp.shared_expert*",
	"model.language_model.layers.8.mlp.shared_expert_gate",
	"model.language_model.layers.8.mlp_hyper_connection*",
	"model.language_model.layers.9.attn_hyper_connection*",
	"model.language_model.layers.9.linear_attn*",
	"model.language_model.layers.9.mlp.gate",
	"model.language_model.layers.9.mlp.shared_expert*",
	"model.language_model.layers.9.mlp.shared_expert_gate",
	"model.language_model.layers.9.mlp_hyper_connection*",
	"model.visual*",
	"mtp.fc_embedding",
	"mtp.fc_hidden",
	"mtp.hyper_connection_mixer.hc_norm",
	"mtp.hyper_connection_mixer.input_mix_weight_down",
	"mtp.hyper_connection_mixer.input_mix_weight_up",
	"mtp.layers.0.attn_hyper_connection.block_inject_weight",
	"mtp.layers.0.attn_hyper_connection.hc_norm",
	"mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
	"mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
	"mtp.layers.0.mlp.experts",
	"mtp.layers.0.mlp.gate",
	"mtp.layers.0.mlp.shared_expert.down_proj",
	"mtp.layers.0.mlp.shared_expert.gate_proj",
	"mtp.layers.0.mlp.shared_expert.up_proj",
	"mtp.layers.0.mlp.shared_expert_gate",
	"mtp.layers.0.mlp_hyper_connection.block_inject_weight",
	"mtp.layers.0.mlp_hyper_connection.hc_norm",
	"mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
	"mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
	"mtp.layers.0.self_attn.indexer.index_qk_proj",
	"mtp.layers.0.self_attn.indexer.k_layernorm",
	"mtp.layers.0.self_attn.indexer.q_layernorm",
	"mtp.layers.0.self_attn.k_norm",
	"mtp.layers.0.self_attn.k_proj",
	"mtp.layers.0.self_attn.o_proj",
	"mtp.layers.0.self_attn.q_norm",
	"mtp.layers.0.self_attn.q_proj",
	"mtp.layers.0.self_attn.v_proj",
	"mtp.pre_fc_norm_embedding",
	"mtp.pre_fc_norm_hidden"
	]
	}
	}