Instructions to use cosimoiaia/Loquace-70m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cosimoiaia/Loquace-70m with Transformers:

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

pipe = pipeline("text-generation", model="cosimoiaia/Loquace-70m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cosimoiaia/Loquace-70m")
model = AutoModelForCausalLM.from_pretrained("cosimoiaia/Loquace-70m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use cosimoiaia/Loquace-70m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cosimoiaia/Loquace-70m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cosimoiaia/Loquace-70m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cosimoiaia/Loquace-70m

SGLang

How to use cosimoiaia/Loquace-70m 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 "cosimoiaia/Loquace-70m" \
    --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": "cosimoiaia/Loquace-70m",
		"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 "cosimoiaia/Loquace-70m" \
        --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": "cosimoiaia/Loquace-70m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cosimoiaia/Loquace-70m with Docker Model Runner:
```
docker model run hf.co/cosimoiaia/Loquace-70m
```

YAML Metadata Warning:The pipeline tag "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Model Card for Loquace-70m

🇮🇹 Loquace-70m 🇮🇹

An exclusively Italian speaking, instruction finetuned, Large Language model. 🇮🇹

The Loquace Italian LLM models are created as a proof-of-concept to evaluate on how language tuning can be achieved using QLoRa by instruct-tunings foundational LLMs using dataset of a specific language.

The QLoRa (https://github.com/artidoro/qlora) method of fine-tuning significantly lower the resources requirements compared to any other methods available, this allow to easily execute the process on significanly larger dataset while still using consumers GPUs and still achieve high accuracy.

Model Description

Loquace-70m is the smallest model of the Loquace family. It was trained using QLoRa on a large dataset of 102k question/answer pairs exclusively in Italian.

The related code can be found at: https://github.com/cosimoiaia/Loquace

Loquace-70m is part of the big Loquace family:

https://huggingface.co/cosimoiaia/Loquace-70m - Based on pythia-70m https://huggingface.co/cosimoiaia/Loquace-410m - Based on pythia-410m https://huggingface.co/cosimoiaia/Loquace-7B - Based on Falcon-7B. https://huggingface.co/cosimoiaia/Loquace-12B - Based on pythia-12B https://huggingface.co/cosimoiaia/Loquace-20B - Based on gpt-neox-20B

Usage

from transformers import (
    AutoTokenizer,
    AutoModelForCausalLM,
    BitsAndBytesConfig
)

tokenizer = AutoTokenizer.from_pretrained("cosimoiaia/Loquace-70m", padding_side="right", use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    "cosimoiaia/Loquace-70m",
    load_in_8bit=True,
    device_map="auto",
    quantization_config=BitsAndBytesConfig(
      load_in_4bit=True,
      llm_int8_has_fp16_weight=False
    )
)

Training

Loquace-70m was trained on a conversational dataset comprising 102k question/answer pairs in Italian language. The training data was constructed by putting together translations from the original alpaca Dataset and other sources like the OpenAssistant dataset. The model was trained for only 10000 iterations and took 6 hours on a single RTX 3090, kindly provided by Genesis Cloud. (https://gnsiscld.co/26qhlf)

Limitations

Loquace-70m may not handle complex or nuanced queries well and may struggle with ambiguous or poorly formatted inputs.
The model may generate responses that are factually incorrect or nonsensical. It should be used with caution, and outputs should be carefully verified.
The training data primarily consists of conversational examples and may not generalize well to other types of tasks or domains.

Dependencies

PyTorch
Transformers library by Hugging Face
Bitsandbites
QLoRa

Downloads last month: 17

cosimoiaia
/

Loquace-70m