Instructions to use cemig-temp/llama3.1-8b-instruct-data-nemotron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cemig-temp/llama3.1-8b-instruct-data-nemotron with Transformers:

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

pipe = pipeline("text-generation", model="cemig-temp/llama3.1-8b-instruct-data-nemotron")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cemig-temp/llama3.1-8b-instruct-data-nemotron")
model = AutoModelForCausalLM.from_pretrained("cemig-temp/llama3.1-8b-instruct-data-nemotron")
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 cemig-temp/llama3.1-8b-instruct-data-nemotron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cemig-temp/llama3.1-8b-instruct-data-nemotron"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cemig-temp/llama3.1-8b-instruct-data-nemotron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cemig-temp/llama3.1-8b-instruct-data-nemotron

SGLang

How to use cemig-temp/llama3.1-8b-instruct-data-nemotron 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 "cemig-temp/llama3.1-8b-instruct-data-nemotron" \
    --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": "cemig-temp/llama3.1-8b-instruct-data-nemotron",
		"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 "cemig-temp/llama3.1-8b-instruct-data-nemotron" \
        --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": "cemig-temp/llama3.1-8b-instruct-data-nemotron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cemig-temp/llama3.1-8b-instruct-data-nemotron with Docker Model Runner:
```
docker model run hf.co/cemig-temp/llama3.1-8b-instruct-data-nemotron
```

See axolotl config

axolotl version: 0.13.0.dev0

base_model: meta-llama/Llama-3.1-8B-Instruct
tokenizer_type: AutoTokenizer
trust_remote_code: true
is_llama_derived_model: true

datasets:
  - path: nvidia/Llama-Nemotron-Post-Training-Dataset
    type:
      system_prompt: ""
      field_instruction: input
      field_input: ""
      field_output: output
      format: |-
        {instruction}
    split: chat

val_set_size: 0.01     

micro_batch_size: 1
gradient_accumulation_steps: 8

sequence_len: 8192             
eval_sequence_len: 8192
pad_to_sequence_len: true     
sample_packing: true          


optimizer: adamw_torch_fused  
learning_rate: 2.0e-5
weight_decay: 0.0
betas: [0.9, 0.999]
eps: 1.0e-8

lr_scheduler: cosine
warmup_steps: 100

bf16: true                      
tf32: true
gradient_checkpointing: true

special_tokens:
  eos_token: "<|eot_id|>"
  pad_token: "<|eot_id|>"

eot_tokens:
  - "<|eot_id|>"

roles_to_train:
  - assistant

train_on_eos: last

save_strategy: steps
save_steps: 100
save_total_limit: 3
save_safetensors: true
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false

logging_steps: 10
output_dir: ./outputs/llama31_full_sft_instruct_data_nemotron
seed: 42

outputs/llama31_full_sft_instruct_data_nemotron

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the nvidia/Llama-Nemotron-Post-Training-Dataset 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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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: 100
training_steps: 849

Training results

Framework versions

Transformers 4.57.1
Pytorch 2.9.0+cu130
Datasets 4.3.0
Tokenizers 0.22.1

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F32

BF16

Model tree for cemig-temp/llama3.1-8b-instruct-data-nemotron

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2740)

this model

cemig-temp
/

llama3.1-8b-instruct-data-nemotron

outputs/llama31_full_sft_instruct_data_nemotron

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for cemig-temp/llama3.1-8b-instruct-data-nemotron

Dataset used to train cemig-temp/llama3.1-8b-instruct-data-nemotron