nbeerbower/Lyra4-Gutenberg2-12B

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Sep 29, 2024License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Warm

nbeerbower/Lyra4-Gutenberg2-12B is a 12 billion parameter language model, fine-tuned from Sao10K/MN-12B-Lyra-v4, with an increased sequence length and a 32768 token context window. It was trained using ORPO on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo datasets, formatted with ChatML. This model is designed for general language tasks, leveraging its extended context and specific DPO fine-tuning.

Loading preview...

Lyra4-Gutenberg2-12B: An ORPO Fine-tuned 12B Model

Lyra4-Gutenberg2-12B is a 12 billion parameter language model developed by nbeerbower, building upon the Sao10K/MN-12B-Lyra-v4 base. This iteration features an increased sequence length compared to its predecessor, Lyra4-Gutenberg-12B, enhancing its ability to process longer contexts up to 32768 tokens.

Key Capabilities & Training:

Performance Insights:

Evaluations on the Open LLM Leaderboard show an average score of 19.74. Specific metrics include:

  • IFEval (0-Shot): 25.85
  • BBH (3-Shot): 33.73
  • MMLU-PRO (5-shot): 28.51

This model is suitable for applications requiring a balance of parameter size and extended context handling, particularly where DPO-style alignment is beneficial.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p