Model · qwen-7b
Qwen-7B
Developer: Alibaba Cloud
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/qwen-7b.json
Fields
- id
- qwen-7b
- identifiers
- huggingface
- Qwen/Qwen-7B
- developer
- Alibaba Cloud
- release_date
- 2023-09-28recorded · sourcenote: arXiv paper (2309.16609) date.
- weights_status
- open
- availability
- available · checked 2026-09-24 · source
- license
- Tongyi Qianwen License Agreement (custom; open for research and commercial use with application)recorded · source
- architecture
- family
- decoder_only
- note
- family read from config 'architectures': ['QWenLMHeadModel'].
- n_layers
- 32recorded · source
- hidden_size
- 4096recorded · source
- n_heads
- 32recorded · source
- vocab_size
- 151936recorded · source
- context_length
- 32768recorded · source
- positional_encoding
- rotary (RoPE), with NTK-aware interpolation and LogN attention scaling for context extensionrecorded · source
- training_data
- Over 2.4 trillion tokens: web text, encyclopedia, books, code, mathematics, multilingual (Chinese, English, code).recorded · source
- techniques
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (Qwen/Qwen-7B@ef3c5c9c57b252f3149c1408daf4d649ec8b6c85) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer, release date, license, positional encoding, training_data set · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer cleanup: removed 3 stale flag(s) · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:reviewed and promoted from staging (0 edge(s) accepted) · by:Wilson Pruitt ·
Parents
No edges recorded.
Children
No edges recorded.
Read in
No station on the reading path has touched this record yet.