Model · zephyr-7b-alpha
zephyr-7b-alpha
Developer: Hugging Face (H4 team)
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/zephyr-7b-alpha.json
Fields
- id
- zephyr-7b-alpha
- identifiers
- huggingface
- HuggingFaceH4/zephyr-7b-alpha
- developer
- Hugging Face (H4 team)
- release_date
- 2023-10-09partial · 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': ['MistralForCausalLM'].
- n_layers
- 32recorded · source
- hidden_size
- 4096recorded · source
- n_heads
- 32recorded · source
- vocab_size
- 32000recorded · source
- context_length
- 32768recorded · source
- n_kv_heads
- 8recorded · source
- positional_encoding
- rotary (RoPE)recorded · sourcenote: Architecture unchanged from mistral-7b-v0-1 (instruction fine-tune).
- training_data
- Filtered UltraChat (SFT) and UltraFeedback (DPO) -- see the trained_on edges below, which carry the sourced detail; this field is a pointer, not a duplicate description.partial · source
- techniques
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (HuggingFaceH4/zephyr-7b-alpha@014792bbb59d04ced3b5a9b8b4dfc926655d958f) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer, fine_tuned_from mistral-7b-v0-1, trained_on ultrachat + ultrafeedback added -- same pattern as zephyr-7b-beta · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer: deduplicated edges (ingest had already resolved these three) · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer cleanup: removed 1 stale flag(s) · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer cleanup: training_data filled · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:preparer cleanup: positional_encoding propagated from an unchanged parent architecture · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:reviewed and promoted from staging (3 edge(s) accepted) · by:Wilson Pruitt ·
Parents
Weights descend
- fine_tuned_from → Mistral 7B (v0.1) declared_by_uploader source HF card metadata base_model: mistralai/Mistral-7B-v0.1. Relation 'finetune' is the Hub's inference (tag), not stated in the card.
Training data
- trained_on → UltraChat declared_by_uploader source HF card metadata datasets: stingning/ultrachat. Often incomplete; confirm which training stage used it.
- trained_on → UltraFeedback declared_by_uploader source HF card metadata datasets: openbmb/UltraFeedback. Often incomplete; confirm which training stage used it.
Children
No edges recorded.
Read in
No station on the reading path has touched this record yet.