Instructions to use PracticalWork/Llama-3.2-1B-Instruct-tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticalWork/Llama-3.2-1B-Instruct-tuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
model = PeftModel.from_pretrained(base_model, "PracticalWork/Llama-3.2-1B-Instruct-tuned")

Transformers

How to use PracticalWork/Llama-3.2-1B-Instruct-tuned with Transformers:

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

pipe = pipeline("text-generation", model="PracticalWork/Llama-3.2-1B-Instruct-tuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PracticalWork/Llama-3.2-1B-Instruct-tuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticalWork/Llama-3.2-1B-Instruct-tuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PracticalWork/Llama-3.2-1B-Instruct-tuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PracticalWork/Llama-3.2-1B-Instruct-tuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PracticalWork/Llama-3.2-1B-Instruct-tuned

SGLang

How to use PracticalWork/Llama-3.2-1B-Instruct-tuned 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 "PracticalWork/Llama-3.2-1B-Instruct-tuned" \
    --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": "PracticalWork/Llama-3.2-1B-Instruct-tuned",
		"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 "PracticalWork/Llama-3.2-1B-Instruct-tuned" \
        --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": "PracticalWork/Llama-3.2-1B-Instruct-tuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PracticalWork/Llama-3.2-1B-Instruct-tuned with Docker Model Runner:
```
docker model run hf.co/PracticalWork/Llama-3.2-1B-Instruct-tuned
```

Llama-3.2-1B-Instruct-tuned / README.md

29thDay

Update README.md

c3cfcc5 verified about 1 year ago

preview code

Raw History Blame Contribute Delete

1.76 kB

metadata

library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
  - base_model:adapter:meta-llama/Llama-3.2-1B-Instruct
  - transformers
pipeline_tag: text-generation
model-index:
  - name: Llama-3.2-1B-Instruct-tuned
    results: []

Llama-3.2-1B-Instruct-tuned

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5964
Perplexity: 4.9351

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.003
train_batch_size: 12
eval_batch_size: 12
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Perplexity
No log	0	0	4.5699	96.5354
No log	0.6011	333	1.7253	5.6141
1.8003	1.2022	666	1.6644	5.2825
1.8003	1.8032	999	1.6342	5.1252
1.6299	2.4043	1332	1.6094	5.0000
1.6299	3	1664	1.5964	4.9351

Framework versions

PEFT 0.16.0
Transformers 4.54.1
Pytorch 2.7.1+cu128
Datasets 4.0.0
Tokenizers 0.21.4