Edit model card
logo voicelab nlp

Trurl 2 -- Polish Llama 2

The new OPEN TRURL is a finetuned Llama 2, trained on over 1.7b tokens (970k conversational Polish and English samples) with a large context of 4096 tokens. TRURL was trained on a large number of Polish data. TRURL 2 is a collection of fine-tuned generative text models with 7 billion and 13 billion parameters. This is the repository for the 13B fine-tuned model, optimized for dialogue use cases.

Overview

TRURL developers Voicelab.AI

Variations Trurl 2 comes in 7B and 13B versions.

Input Models input text only.

Output Models generate text only.

Model Architecture Trurl is an auto-regressive language model that uses an optimized transformer architecture.

Training Data Params Content Length Num. Samples Num. Tokens start LR
Trurl 2 A new mix of private and publicly available online data without MMLU 7B 4k 855k 1.19b 2.0 x 10-5
Trurl 2 A new mix of private and publicly available online data with MMLU 13B 4k 970k 1.7b 2.0 x 10-5
Trurl 2 Academic A new mix of private and publicly available online data without MMLU 13B 4k 855k 1.19b 2.0 x 10-5

Training data

The training data includes Q&A pairs from various sources including Alpaca comparison data with GPT, Falcon comparison data, Dolly 15k, Oasst1, Phu saferlfhf, ShareGPT version 2023.05.08v0 filtered and cleaned, Voicelab private datasets for JSON data extraction, modification, and analysis, CURLICAT dataset containing journal entries, dataset from Polish wiki with Q&A pairs grouped into conversations, MMLU data in textual format, Voicelab private dataset with sales conversations, arguments and objections, paraphrases, contact reason detection, and corrected dialogues.

Intended Use

Trurl 2 is intended for commercial and research use in Polish and English. Tuned models are intended for assistant-like chat, but also adapted for a variety of natural language generation tasks.

Evaluation Results

Model Size hellaswag arc_challenge MMLU
Llama-2-chat 7B 78.55% 52.9% 48.32%
Llama-2-chat 13B 81.94% 59.04% 54.64%
Trurl 2.0 (with MMLU) 13B 80.09% 59.30% 78.35%
Trurl 2.0 (no MMLU) 13B TO-DO TO-DO TO-DO
Trurl 2.0 (no MMLU) 7b 75.29% 53.41% 50.0%
trurl graphic

Examples

Polish language

HUMAN: What’s the point of training you on Polish?

TRURL: The point of training me on Polish, or any other language, is to enable me to understand and respond to queries and questions in that language. This allows people who speak that language to use me as a helpful tool for finding information, answering questions, and completing tasks. By training me on a wide variety of texts in Polish, I can learn about the culture, history, and language of Poland, and be able to provide more accurate and relevant responses to users. Additionally, training me on multiple languages allows me to be useful to a wider range of people, regardless of their native language.

Stanisław Lem

HUMAN: who is Trurl from Stanisław Lem book?

TRURL: Trurl is a character in a series of short stories by Polish science fiction writer Stanisław Lem. The stories feature Trurl and another character, Klapaucius, who are both inventors and explorers of the universe. They use their advanced technology and knowledge to solve various problems and encounter strange and fantastical creatures along the way. The stories often explore themes of science, technology, and the nature of intelligence and consciousness.

The description of original Trurl generated by TRURL 2.0. Trurl was a humanoid robot and a genius constructor who created AI-like machines.

HUMAN: why are you named Trurl?

TRURL: I was named after the character Trurl from the short stories by Stanisław Lem. My creators, the VoiceLab AI team, were inspired by the character’s intelligence and creativity, and they wanted to create an AI assistant that embodied those qualities. They also wanted to give me a unique and memorable name, and Trurl seemed like the perfect fit.

Example use

LLM

Simply pass a prompt to a model and decode an output. Model will continue writing text based on sample you provided.

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained("Voicelab/trurl-2-13b")
model = LlamaForCausalLM.from_pretrained("Voicelab/trurl-2-13b")

prompt = "Yesterday, when I was"

tokenized_prompt = tokenizer(prompt, return_tensors="pt")

model.eval()
with torch.no_grad():
    print(tokenizer.decode(
        model.generate(**tokenized_prompt, max_new_tokens=200)[0],
        skip_special_tokens=True))

Chat

When using TRURL in a chat mode you should remember to use Llama 2 conversation template like in the example below.

import torch
from transformers import LlamaForCausalLM, LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained("Voicelab/trurl-2-13b")
model = LlamaForCausalLM.from_pretrained("Voicelab/trurl-2-13b")

prompt = """
<s>[INST] <<SYS>>  You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.
Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.
Please ensure that your responses are socially unbiased and positive in nature.\n\n
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.
If you don't know the answer to a question, please don't share false information. <</SYS>>

What was the reason for calling in the conversation below? \n\n
AGENT: Hello, Bank of Albion, this is Mata Hari. How can I help you?
CLIENT: Hi. I've been locked out from my Internet account. I need your help.
AGENT: (yy) Yes, of course, I'll do my best to help you. But I need to find out why the locking-out happened. (yy) In order to ascertain that, I'll ask you a couple of questions to confirm your identity. I'm going to need your full name.
CLIENT: Lizz Truss.
AGENT: Thank you. Now I need your personal identification number.
CLIENT: Fourteen, two hundred thirty-one, thirty-eight, twenty-nine, sixty-five.
AGENT: Thank you. Now I need your client ID number. The client ID number is the eight digits we assigned to you at the very beginning, on conclusion of the contract.
CLIENT: OK. Give me a moment. I have to find it.
AGENT: (mhm) You'll find… You'll find it in the contract.
CLIENT: Yes, yes. I can see it. Sixty-five, twenty-nine, thirty-eight, thirty-one.
AGENT: Thank you. One final security question. Do you have any deposits in our bank?
CLIENT: No, no. I don't have any deposits in this bank.
AGENT: Thank you. Your identity has been (yy) confirmed. (yy) I can see that the account has been blocked, indeed, and you won't be able to log in via the Internet (yy) because (yy) the identity document which is listed for reference has expired. (yy) From what I can see, your identity document expired some time ago. Have you been issued a new one?
CLIENT: Well, no. I think my ID is still valid, you know. I didn't even know.
AGENT: Well, no... Your ID expired at the end of March. Well, almost at the end. Your old ID had been valid until 26 March. (yy) For that reason, your accout has been blocked, because you haven't notified us about the ID change for a few months. We are not interested if the ID document has been officialy reissued. (...) On our end, what matters is whether the document listed for our reference is valid (yy) so without a valid document I can't unlock your accout. 
CLIENT: But I have to carry out an operation right now, so this is sort of problematic.
AGENT: I understand. But (yy) you are obligated, as an account holder, to notify the bank about any changes pending (yy), regrding, for example, your home address or phone number. Now, one of such safeguards protecting your… (yy) money, your sensitive data, is precisely about having a valid identification document. Since this is missing in your case, the account has been blocked. Now, I don't think this would have caught you off guard, because we always remind our customers that their ID is about to expire. When the ID is nearing expiration, we display relevant messages at least sixty days in advance. They appear once you've logged in, at the very top of the screen, there is a notification that (yy) the ID is about to expire (yy), so, well... The bank did notify you about this issue. Now, how you chose to act on this information was your choice, right? In any case, at this point, in order to unlock your accout, our protocols require that you produce a new identification document at one of our branches. You shall provide information concerning the new document number, new valid-thru date, and only then will you be able to use your account again. I can schedule an appointment with a consultant at our branch for you. What locality would you prefer?
CLIENT: Well, I'm not sure if I should share such information with you.
AGENT: And may I ask why exactly you are unsure? After all, you're calling a bank that runs your account, right?
CLIENT: Right, you know what, I need to go now. Good bye.
AGENT: (yy) Miss… [/INST]

"""

tokenized_prompt = tokenizer(prompt, return_tensors="pt")

model.eval()
with torch.no_grad():
    print(tokenizer.decode(
        model.generate(**tokenized_prompt, max_new_tokens=200)[0],
        skip_special_tokens=True))

To get the expected features and performance for the chat versions, a specific Llama 2 formatting needs to be followed, including the INST and <<SYS>> tags, BOS and EOS tokens, and the whitespaces and breaklines in between (we recommend calling strip() on inputs to avoid double-spaces). See reference code in github for details: chat_completion.

<s>[INST] <<SYS>> system prompt <</SYS>>
human prompt [/INST]
gpt response </s>
<s>[INST] human prompt [/INST]
gpt response </s>

Ethical Considerations and Limitations

Trurl 2, same as a Llama 2, is a new technology that carries risks with use. Testing conducted to date has been in Polish and English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Trurl 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Trurl 2, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see the Meta's Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/

Authors

The model was trained by NLP Research Team at Voicelab.ai.

You can contact us here.

Quantized models:

The work was supported by #NASK

Downloads last month
1,068
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for Voicelab/trurl-2-13b

Adapters
1 model
Finetunes
1 model
Quantizations
3 models

Spaces using Voicelab/trurl-2-13b 31