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, text2text-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-retrieval, time-series-forecasting, text-to-video, image-text-to-text, 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, any-to-any, other

LLammas-translate 🐑

Llama-2-7B finetuned in three stages:

  1. 5B tokens of CulturaX (75% Estonain, 25% English)
  2. 1M English->Estonian sentence-pairs from CCMatrix (500000), WikiMatrix (400000), Europarl (50000), and OpenSubtitles (50000) as Alpaca-style translation instructions, 25% of the examples are given in opposite direction (Estonian->Englih)
  3. Alpaca-cleaned, Alpaca-est, OASST1 top-1 English conversations, CoT and FLAN-V2 following open-instruct (both 10,000), WMT18 English-Estonian translation development data (as documents), general MTee validation English-Estonian held-out data

Alpaca-est is an instruction dataset generated for Estonian with gpt-3.5-turbo-0613, following Alpaca.

Using the model in a conversational pipeline:

from transformers import pipeline, Conversation
import torch

pipe = pipeline("conversational", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {"role": "user", "content": "Tere!"},
    {"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"},
    {"role": "user", "content": "Kuidas alustada kirja kirjutamist?"}
]

conversation = Conversation(messages)
conversation = pipe(conversation)

Conversational format:

<|user|>
Tere!
<|assistant|>
Tere! Kas saaksin teid kuidagi aidata?</s>
<|user|>
Kuidas alustada kirja kirjutamist?
<|assistant|>
Kirja kirjutamiseks alustage tervitusega, näiteks "Tere!" või "Tere hommikust!". Seejärel tutvustage ennast ja mainige, kellega kirjutate. Kirjeldage oma mõtteid või küsimusi, mida soovite arutada. Lõpetage kiri viisakalt, näiteks "Tänan teid tähelepanu eest!" või "Parimate soovidega!"</s>
Downloads last month
16
Safetensors
Model size
6.74B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including tartuNLP/Llammas-translate