Instructions to use garboab/Greta-1b-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use garboab/Greta-1b-Preview with Transformers:

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

pipe = pipeline("text-generation", model="garboab/Greta-1b-Preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("garboab/Greta-1b-Preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use garboab/Greta-1b-Preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/garboab/Greta-1b-Preview

SGLang

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

Docker Model Runner
How to use garboab/Greta-1b-Preview with Docker Model Runner:
```
docker model run hf.co/garboab/Greta-1b-Preview
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Greta-1b-Preview

Model Details

Current state

This model is currently still in post-training and is pre-released as a preview checkpoint with gated access only.

How to run

Notice: See jinja-template for formats and tool parsing

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("garboab/Greta-1b-Preview", use_fast=True, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    "garboab/Greta-1b-Preview",
    trust_remote_code=True,
    device_map="auto",
)

tools = [
    {
        "type": "function",
        "name": "search",
        "description": "Search the web for information.",
        "parameters": {
            "type": "object",
            "properties": {
                "q": {
                    "type": "string",
                    "description": "Query to search for.",
                },
            },
            "required": ["q"],
        },
    },
]

text = tokenizer.apply_chat_template(
    [
        {"role": "tools", "content": tools},
        {"role": "user", "content": "Where can I read more about Garbo AI?"},
    ],
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,
)

input_ids = tokenizer(
    text,
    add_bos_token=True,
    return_tensors="pt"
).input_ids

output_ids = model.generate(
    input_ids.cuda(),
    max_new_tokens=1024,
    do_sample=True,
    temperature=0.1
)

print(tokenizer.decode(output_ids[0], skip_special_tokens=True).strip())

Downloads last month: 109

Safetensors

Model size

1B params

Tensor type

F32

BF16