Model · platypus2-13b
Platypus2-13B
Developer: Cole Hunter and Ariel Lee (Platypus project, garage-bAInd); paper by Lee, Hunter and Ruiz
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/platypus2-13b.json
Fields
- id
- platypus2-13b
- identifiers
- huggingface
- garage-bAInd/Platypus2-13B
- developer
- Cole Hunter and Ariel Lee (Platypus project, garage-bAInd); paper by Lee, Hunter and Ruiz
- release_date
- 2023-08-05partial · sourcenote: HF repo creation date (2023-08-05). The Platypus paper (arXiv 2308.07317) is dated 2023-08-14.
- weights_status
- open
- availability
- available · checked 2026-09-24 · source
- license
- cc-by-nc-sa-4.0partial · sourcenote: From HF card metadata (`license: cc-by-nc-sa-4.0`). The card text separately says 'License for base weights: Non-Commercial Creative Commons license (CC BY-NC-4.0)' and does not mention the Llama 2 license. Not reconciled; reviewer check.
- architecture
- family
- decoder_only
- note
- family from config 'architectures' and the card ('based on the LLaMA2 transformer architecture'). Positional encoding left not_recorded, matching llama-2-13b.
- n_layers
- 40recorded · source
- hidden_size
- 5120recorded · source
- n_heads
- 40recorded · source
- vocab_size
- 32000recorded · source
- context_length
- 4096recorded · source
- n_kv_heads
- 40recorded · source
- positional_encoding
- nullnot_recorded
- training_data
- Open-Platypus, a STEM and logic dataset (released by the Platypus authors as a subset of other open datasets).recorded · sourcenote: Card: 'trained using STEM and logic based dataset garage-bAInd/Open-Platypus'. Paper abstract: 'our curated dataset Open-Platypus, that is a subset of other open datasets and which we release to the public'.
- techniques
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (garage-bAInd/Platypus2-13B@dc1024c1b9df38f57f6436a02d31706cb0deaa01) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer, release-date note, license note, training data, 2 edges (fine_tuned_from llama-2-13b, trained_on open-platypus); sources: card, arXiv 2308.07317 · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:reviewed and promoted from staging (2 edge(s) accepted) · by:Wilson Pruitt ·
Parents
Weights descend
- fine_tuned_from → Llama-2-13b-hf declared source Card: 'Platypus-13B is an instruction fine-tuned model based on the LLaMA2-13B transformer architecture'; 'instruction fine-tuned using LoRA on 1 A100 80GB'. Uploader garage-bAInd is the developer (card: trained by Cole Hunter & Ariel Lee). 'Based on ... architecture' alone would not show weight descent; the LoRA fine-tuning statement plus the Llama 2 tokenizer/config values do. The paper's abstract also describes 'fine-tuning and merging LoRA modules'; this card does not say whether a merge step produced this checkpoint.
Training data
- trained_on → Open-Platypus declared source Card metadata and text: garage-bAInd/Open-Platypus. Uploader is the dataset's builder.
Children
Weights descend
- ← merged_from OpenOrca-Platypus2-13B declared source Card: 'OpenOrca-Platypus2-13B is a merge of garage-bAInd/Platypus2-13B and Open-Orca/OpenOrcaxOpenChat-Preview2-13B.' The card does not state the merge method, weights or ratios. Parent 1 of 2. Trained by Cole Hunter & Ariel Lee per the card.
Read in
No station on the reading path has touched this record yet.