FLAMA-0.1-3B / README.md
xaviviro's picture
Update README.md
e7106d0
|
raw
history blame
2.01 kB
metadata
license: apache-2.0
base_model: openlm-research/open_llama_3b_v2
datasets:
  - xaviviro/oasst1_ca
tags:
  - finetune
  - chatml
  - gpt4
  - catalan
model-index:
  - name: FLAMA-0.1-3B
    results: []
library_name: transformers
widget:
  - text: |
      <|im_start|>user
       Qui va ser Isaac Newton?<|im_end|>
      <|im_start|>assistant
language:
  - ca
  - en

FLAMA: Model 3B ChatML en Catal脿. Versi贸 0.1

FLAMA 茅s el primer model petit 3B en catal脿. 脡s el resultat de finetunejar el model open_llama_3b_v2 amb les instruccions d'OpenAssistant tradu茂des autom脿ticament al catal脿 amb recursos de Helsinki-NLP i tractades en format ChatML.

馃憠馃徎 Format GGUF i quantitzat

Prompt Template

FLAMA usa ChatML com a prompt template:

<|im_start|>user
Qui va ser Isaac Newton?<|im_end|>
<|im_start|>assistant\n

Refer猫ncies

@software{xaviviro2023flama,
  author = {xaviviro},
  title = {FLAMA: Model 3B ChatML en Catal脿. Versi贸 0.1},
  month = December,
  year = 2023,
  url = {https://huggingface.co/xaviviro/FLAMA-0.1-3B}
}
@software{openlm2023openllama,
  author = {Geng, Xinyang and Liu, Hao},
  title = {OpenLLaMA: An Open Reproduction of LLaMA},
  month = May,
  year = 2023,
  url = {https://github.com/openlm-research/open_llama}
}
@software{together2023redpajama,
  author = {Together Computer},
  title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},
  month = April,
  year = 2023,
  url = {https://github.com/togethercomputer/RedPajama-Data}
}
@article{touvron2023llama,
  title={Llama: Open and efficient foundation language models},
  author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and others},
  journal={arXiv preprint arXiv:2302.13971},
  year={2023}
}