Instructions to use manucif/latamgpt-1b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use manucif/latamgpt-1b-sft with Transformers:

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

pipe = pipeline("text-generation", model="manucif/latamgpt-1b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("manucif/latamgpt-1b-sft")
model = AutoModelForCausalLM.from_pretrained("manucif/latamgpt-1b-sft", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use manucif/latamgpt-1b-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/manucif/latamgpt-1b-sft

SGLang

How to use manucif/latamgpt-1b-sft 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 "manucif/latamgpt-1b-sft" \
    --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": "manucif/latamgpt-1b-sft",
		"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 "manucif/latamgpt-1b-sft" \
        --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": "manucif/latamgpt-1b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use manucif/latamgpt-1b-sft with Docker Model Runner:
```
docker model run hf.co/manucif/latamgpt-1b-sft
```

latamgpt-1b-sft

Full supervised fine-tune of meta-llama/Llama-3.2-1B on a Latin American instruction mixture, with sequence packing and assistant-only loss masking.

Training data

Dataset	Role
`latam-gpt/wikipedia-qa-iberoamerica-clean`	Iberoamerican QA
`latam-gpt/tulu-3-sft-mixture-no-identity-clean`	General SFT mixture
`latam-gpt/sft-mcqa-unified-clean`	Multiple-choice QA
`latam-gpt/self-identity-v3-clean`	Self-identity
`latam-gpt/copuchatV2-clean`	Chilean conversational

After tokenization with the Llama 3 chat template and FFD packing at 4096 tokens (99.16% packing efficiency), the training set is 175,995 packed sequences (~721M tokens) with 119,573 validation examples.

Training setup

Base model: meta-llama/Llama-3.2-1B
Method: Full fine-tune (no LoRA)
Sequence length: 4096, packed with assistant-only loss masking
Epochs: 2
Learning rate: 1e-5 (cosine, 3% warmup)
Batch: 8 per device × 8 grad accumulation × 2 GPUs = 128 effective
Precision: bf16 + DeepSpeed ZeRO-2 + gradient checkpointing + Flash Attention 2
Hardware: 2× H100 80GB
Wall time: ~7.5h

Results

Metric	Value
`train_loss`	0.8579
`eval_loss`	0.8910
`epoch`	2.0
`train_samples`	175,995

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tok = AutoTokenizer.from_pretrained("latam-gpt/latamgpt-1b-sft")
model = AutoModelForCausalLM.from_pretrained("latam-gpt/latamgpt-1b-sft", torch_dtype="bfloat16", device_map="auto")

messages = [{"role": "user", "content": "¿Cuál es la capital de Chile?"}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

License

Inherits the Llama 3.2 Community License from the base model.

Downloads last month: 476

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for manucif/latamgpt-1b-sft

Base model

meta-llama/Llama-3.2-1B

Finetuned

(942)

this model