Instructions to use Ba2han/augment-nvfp4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/augment-nvfp4a16 with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/augment-nvfp4a16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ba2han/augment-nvfp4a16")
model = AutoModelForCausalLM.from_pretrained("Ba2han/augment-nvfp4a16")
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 Ba2han/augment-nvfp4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/augment-nvfp4a16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/augment-nvfp4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/augment-nvfp4a16

SGLang

How to use Ba2han/augment-nvfp4a16 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 "Ba2han/augment-nvfp4a16" \
    --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": "Ba2han/augment-nvfp4a16",
		"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 "Ba2han/augment-nvfp4a16" \
        --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": "Ba2han/augment-nvfp4a16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Ba2han/augment-nvfp4a16 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/augment-nvfp4a16 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/augment-nvfp4a16 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/augment-nvfp4a16 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/augment-nvfp4a16",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/augment-nvfp4a16 with Docker Model Runner:
```
docker model run hf.co/Ba2han/augment-nvfp4a16
```

augment-nvfp4a16 / config.json

Ba2han

Upload folder using huggingface_hub

a1e3a1d verified 2 months ago

raw

history blame contribute delete

2.47 kB

	{
	"architectures": [
	"Lfm2MoeForCausalLM"
	],
	"bos_token_id": 1,
	"conv_L_cache": 3,
	"conv_bias": false,
	"dtype": "bfloat16",
	"eos_token_id": 7,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 7168,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_name": "augment-multi-ft2/checkpoint-1000",
	"model_type": "lfm2_moe",
	"moe_intermediate_size": 1792,
	"norm_eps": 1e-05,
	"norm_topk_prob": true,
	"num_attention_heads": 32,
	"num_dense_layers": 2,
	"num_experts": 32,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 24,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"quantization_config": {
	"config_groups": {
	"NVFP4A16": {
	"format": "nvfp4-pack-quantized",
	"input_activations": null,
	"output_activations": null,
	"targets": [
	"Linear"
	],
	"weights": {
	"actorder": null,
	"block_structure": null,
	"dynamic": false,
	"group_size": 16,
	"num_bits": 4,
	"observer": "memoryless_minmax",
	"observer_kwargs": {},
	"scale_dtype": "torch.float8_e4m3fn",
	"strategy": "tensor_group",
	"symmetric": true,
	"type": "float",
	"zp_dtype": null
	}
	}
	},
	"format": "nvfp4-pack-quantized",
	"global_compression_ratio": null,
	"ignore": [
	"model.embed_tokens",
	"lm_head",
	"re:.norm.",
	"re:.*gate$",
	"re:.\\.conv\\..",
	"re:^model\\.layers\\.0\\..*",
	"re:^model\\.layers\\.1\\..*",
	"re:^model\\.layers\\.23\\..*"
	],
	"kv_cache_scheme": null,
	"quant_method": "compressed-tensors",
	"quantization_status": "compressed",
	"sparsity_config": {},
	"transform_config": {},
	"version": "0.14.0.1"
	},
	"rope_parameters": {
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"routed_scaling_factor": 1.0,
	"tie_word_embeddings": true,
	"transformers_version": "5.3.0",
	"unsloth_version": "2026.3.4",
	"use_cache": false,
	"use_expert_bias": true,
	"vocab_size": 65536
	}