Model · redpajama-incite-7b-base
RedPajama-INCITE-7B-Base
Developer: Together Computer (with Ontocord.ai, ETH DS3Lab, Stanford CRFM, Université de Montréal)
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/redpajama-incite-7b-base.json
Fields
- id
- redpajama-incite-7b-base
- identifiers
- huggingface
- togethercomputer/RedPajama-INCITE-7B-Base
- developer
- Together Computer (with Ontocord.ai, ETH DS3Lab, Stanford CRFM, Université de Montréal)
- release_date
- 2023-05-04partial · sourcenote: HF repo creation date; may predate or postdate public release.
- weights_status
- open
- availability
- available · checked 2026-09-24 · source
- license
- apache-2.0partial · sourcenote: From HF card metadata (uploader-declared); confirm against the license text.
- architecture
- family
- decoder_only
- note
- Card/tags: GPT-NeoX architecture. Config was not independently checked for rotary_pct/positional encoding this session.
- n_layers
- 32recorded · source
- hidden_size
- 4096recorded · source
- n_heads
- 32recorded · source
- vocab_size
- 50432recorded · source
- context_length
- 2048recorded · source
- positional_encoding
- nullnot_recorded
- training_data
- RedPajama-Data-1T (~1 trillion tokens), a reproduction of the LLaMA training mix. Card, Training Data: 'Please refer to togethercomputer/RedPajama-Data-1T'; Num of Tokens: 1.001T.recorded · source
- techniques
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (togethercomputer/RedPajama-INCITE-7B-Base@78f7e482443971f4873ba3239f0ac810a367833b) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer set; dataset edge rejected pending a RedPajama record · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer cleanup: removed 2 stale flag(s), filled training_data · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:reviewed and promoted from staging (0 edge(s) accepted) · by:Wilson Pruitt ·date:2026-09-24 · change:trained_on redpajama-data-1t added now the dataset record exists · by:wilson-pruitt + claude ·
Parents
Training data
- trained_on → RedPajama-Data-1T declared source Developer's card (Together is the uploader and developer): 'Training Data: Please refer to togethercomputer/RedPajama-Data-1T'; also in card metadata `datasets`.
Children
Weights descend
- ← fine_tuned_from RedPajama-INCITE-7B-Instruct declared source Card lists 'Base Model: RedPajama-INCITE-7B-Base' and says the model 'was fine-tuned for few-shot applications on the data of GPT-JT'. No `base_model` metadata; the relation rests on the card text.
Read in
No station on the reading path has touched this record yet.