Hugging Face's logo

DebateLabKIT
/
Llama-3.1-Argunaut-1-8B-SFT

Text Generation
Transformers
Safetensors
llama
logic
argumentation
critical-thinking
argument-mapping
trl
sft
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
Llama-3.1-Argunaut-1-8B-SFT / README.md
ggbetz's picture
ggbetz
Update README.md
16954e7 verified
preview code
|
raw
history blame
2.44 kB
metadata
license: llama3.1
datasets:
  - DebateLabKIT/deepa2-conversations
  - DebateLabKIT/deep-argmap-conversations
  - allenai/tulu-3-sft-mixture
base_model:
  - meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
  - logic
  - argumentation
  - critical-thinking
  - argument-mapping
  - trl
  - sft

Model Card for Llama-3.1-Argunaut-1-8B-SFT

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct. It has been trained using TRL.

Quick start 

from transformers import pipeline

question = "Are you familiar with Argdown syntax? What's its purpose?"
generator = pipeline("text-generation", model="DebateLabKIT/Llama-3.1-Argunaut-1-8B-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Evals

SFT dataset mixture

dataset weight (examples) weight (tokens)
DebateLabKIT/deepa2-conversations 25% 49%
DebateLabKIT/deep-argmap-conversations 25% 18%
allenai/tulu-3-sft-mixture 50% 33%

Training procedure

Trained with SFT on 1M examples and for 1 epoch with

  • context length 8196
  • packing (trl implementation)
  • spectrum (top 30 percent)
# Training parameters
num_train_epochs: 1
per_device_train_batch_size: 8
gradient_accumulation_steps: 2
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
learning_rate: 5.0e-6  # following _Tülu 3_ recipe
lr_scheduler_type: cosine
warmup_ratio: 0.1

Hardware: 2 x H100 GPUs.

This work was performed on the HoreKa supercomputer funded by the Ministry of Science, Research and the Arts Baden-Württemberg and by the Federal Ministry of Education and Research.

Framework versions

  • TRL: 0.12.1
  • Transformers: 4.46.3
  • Pytorch: 2.4.1
  • Datasets: 3.1.0
  • Tokenizers: 0.20.3

Credits

This work wouldn't be possible without all the great contributions from the open LLM community. Thank you! Special kudos go to