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

Libraries

How to use SZTAKI-HLT/Llama-3.2-1B-HuAMR with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SZTAKI-HLT/Llama-3.2-1B-HuAMR")
model = AutoModelForCausalLM.from_pretrained("SZTAKI-HLT/Llama-3.2-1B-HuAMR", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SZTAKI-HLT/Llama-3.2-1B-HuAMR with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SZTAKI-HLT/Llama-3.2-1B-HuAMR

SGLang

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

Docker Model Runner
How to use SZTAKI-HLT/Llama-3.2-1B-HuAMR with Docker Model Runner:
```
docker model run hf.co/SZTAKI-HLT/Llama-3.2-1B-HuAMR
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Llama-3.2-1B-HuAMR

Model Details

Model Description

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Model type: Abstract Meaning Representation parser
Language(s) (NLP): Hungarian

Model Sources [optional]

Repository: GitHub Repo

Training Details

Training Procedure

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 1
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: AdamW
lr_scheduler_type: linear
max_grad_norm: 0.3

Metrics

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

Framework versions

Transformers 4.34.1
Pytorch 2.3.0+cu118
Datasets 2.19.0
Tokenizers 0.19.1

Downloads last month: 15

Safetensors

Model size

1B params

Tensor type

F32

Model tree for SZTAKI-HLT/Llama-3.2-1B-HuAMR

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1804)

this model

Quantizations

1 model

SZTAKI-HLT
/

Llama-3.2-1B-HuAMR