Model · gpt-neo-125m
gpt-neo-125m
Developer: EleutherAI
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/gpt-neo-125m.json
Fields
- id
- gpt-neo-125m
- identifiers
- huggingface
- EleutherAI/gpt-neo-125m
- developer
- EleutherAI
- release_date
- 2022-03-02partial · sourcenote: HF repo creation date; may predate or postdate public release.
- weights_status
- open
- availability
- available · checked 2026-09-24 · source
- license
- mitpartial · sourcenote: From HF card metadata (uploader-declared); confirm against the license text.
- architecture
- family
- decoder_only
- note
- family read from config 'architectures': ['GPTNeoForCausalLM'].
- n_layers
- 12recorded · source
- hidden_size
- 768recorded · source
- n_heads
- 12recorded · source
- vocab_size
- 50257recorded · source
- context_length
- 2048recorded · source
- positional_encoding
- learned_absoluterecorded · sourcenote: Code: wpe = nn.Embedding(max_position_embeddings, ...), same as gpt-neo-2-7b.
- activation
- GELU (tanh approximation, config 'gelu_new')recorded · source
- training_data
- The Pile, an 825 GiB curated English text corpus (EleutherAI). Same training recipe as the 2.7B model.recorded · source
- techniques
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (EleutherAI/gpt-neo-125m@21def0189f5705e2521767faed922f1f15e7d7db) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer, positional encoding, activation set; trained_on accepted · 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 (1 edge(s) accepted) · by:Wilson Pruitt ·
Parents
Training data
- trained_on → The Pile declared_by_uploader source Card metadata datasets: EleutherAI/pile. Consistent with the gpt-neo-2-7b record, same family/release.
Children
No edges recorded.
Read in
No station on the reading path has touched this record yet.