Instructions to use smohammadi/qated-nvfp4-llama3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smohammadi/qated-nvfp4-llama3B with Transformers:

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

pipe = pipeline("text-generation", model="smohammadi/qated-nvfp4-llama3B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("smohammadi/qated-nvfp4-llama3B")
model = AutoModelForMultimodalLM.from_pretrained("smohammadi/qated-nvfp4-llama3B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use smohammadi/qated-nvfp4-llama3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smohammadi/qated-nvfp4-llama3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smohammadi/qated-nvfp4-llama3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/smohammadi/qated-nvfp4-llama3B

SGLang

How to use smohammadi/qated-nvfp4-llama3B 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 "smohammadi/qated-nvfp4-llama3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smohammadi/qated-nvfp4-llama3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "smohammadi/qated-nvfp4-llama3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smohammadi/qated-nvfp4-llama3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use smohammadi/qated-nvfp4-llama3B with Docker Model Runner:
```
docker model run hf.co/smohammadi/qated-nvfp4-llama3B
```

See axolotl config

axolotl version: 0.13.0.dev0

base_model: meta-llama/Llama-3.2-3B
hub_model_id: smohammadi/qat-nvfp4-llama3B

load_in_8bit: false
load_in_4bit: false
strict: false

  #chunked_cross_entropy: true
  #plugins:
  #  - axolotl.integrations.liger.LigerPlugin

liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
  #liger_fused_linear_cross_entropy: true

datasets:
  - path: yahma/alpaca-cleaned
    type: alpaca
    split: train[:95%]

output_dir: ./outputs/bf16_out/
dataset_prepared_path: ./outputs/qat_out/dataset_prepared

sample_packing: false #true
sequence_len: 4096
flash_attention: true
  #flex_attention: true
  #flex_attn_compile_kwargs:
  # dynamic: false
  #mode: max-autotune-no-cudagraphs
quantization:
  activation_dtype: nvfp4
  weight_dtype: nvfp4
  group_size: 16 # only group_size of 16 is supported with nvfp4

wandb_project: qat_v2
wandb_entity: 
wandb_watch:
wandb_name: bf16-nvfp4
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 64
num_epochs: 1
optimizer: adamw_torch_fused
gradient_checkpointing: true

cosine_constant_lr_ratio: 0
cosine_min_lr_ratio: 1.0
learning_rate: 2e-5
save_only_model: true
bf16: true

resume_from_checkpoint:
logging_steps: 1

evals_per_epoch: 1
saves_per_epoch: 1

warmup_ratio: 0.1
weight_decay: 0.0

special_tokens:
  pad_token: <|finetune_right_pad_id|>

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

qat-nvfp4-llama3B

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the yahma/alpaca-cleaned dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 76
training_steps: 769

Training results

Framework versions

Transformers 4.55.4
Pytorch 2.8.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for smohammadi/qated-nvfp4-llama3B

Base model

meta-llama/Llama-3.2-3B

Finetuned

(457)

this model

smohammadi
/

qated-nvfp4-llama3B

qat-nvfp4-llama3B

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for smohammadi/qated-nvfp4-llama3B

Dataset used to train smohammadi/qated-nvfp4-llama3B