Quantization made by Richard Erkhov.
diablo-italian-base-1.3b - bnb 8bits
Original model description:
license: mit
language:
- it
pipeline_tag: text-generation
Model: DIABLO 1.3B 🔥
Lang: IT
Model description
This model is a causal language model for the Italian language, based on a GPT-like [1] architecture (more specifically, the model has been obtained by modifying Meta's XGLM architecture [2] and exploiting its 1.7B checkpoint).
The model has ~1.3B parameters and a vocabulary of 50.335 tokens. It is a foundation model, pre-trained for causal language modeling, so it is mainly suitable for basic natural language generation, and you will have to fine-tune it in order to use it on more specific downstream tasks.
Quick usage
In order to use the model for inference on GPU, the following pipeline is needed:
1from transformers import AutoTokenizer, AutoModelForCausalLM
2import torch
3from transformers import pipeline
4
5tokenizer = AutoTokenizer.from_pretrained("osiria/diablo-italian-base-1.3b")
6model = AutoModelForCausalLM.from_pretrained("osiria/diablo-italian-base-1.3b", torch_dtype=torch.float16)
7
8device = torch.device("cuda")
9model = model.to(device)
10
11pipeline_nlg = pipeline("text-generation", model = model, tokenizer = tokenizer, device = 0)
12pipeline_nlg("Ciao, mi chiamo Marco Rossi e")
13
14# [{'generated_text': 'Ciao, mi chiamo Marco Rossi e sono un blogger italiano.'}]
Limitations
The model might behave erratically when presented with prompts which are too far away from its pre-training and, because of the probabilistic nature of its generation, it might occasionally produce biased or offensive content with respect to gender, race, ideologies, and political or religious beliefs.
These limitations imply that the model and its outputs should be used with caution, and should not be involved in situations that require the generated text to be fair or true.
References
License
The model is released under MIT license
