Model · llama-2-7b-chat
Llama 2-Chat 7B
Developer: Meta
Availability: gated · checked 2026-09-24 · source
HF gate: manual approval.
Raw record: /data/models/llama-2-7b-chat.json
Fields
- id
- llama-2-7b-chat
- identifiers
- huggingface
- meta-llama/Llama-2-7b-chat-hfmeta-llama/Llama-2-7b-chat
- developer
- Meta
- release_date
- 2023-07-18recorded · source
- weights_status
- open
- availability
- gated · checked 2026-09-24 · sourcenote: HF gate: manual approval.
- license
- Llama 2 Community License Agreement (research and commercial use; licensees with >700M monthly active users on the release date must request a separate license from Meta).recorded · source
- architecture
- family
- decoder_only
- note
- Inherits Llama 2 7B's architecture; Meta's HF config is gated, so no values recorded here.
- n_layers
- nullnot_recorded
- hidden_size
- nullnot_recorded
- n_heads
- nullnot_recorded
- vocab_size
- nullnot_recorded
- positional_encoding
- nullnot_recorded
- training_data
- Supervised fine-tuning plus RLHF on Meta-collected human preference data; see paper sec. 3.partial · source
- techniques
- instruction-tuningrlhf
- primary_sources
- record_history
- date:2026-09-24 · change:created from primary sources (Phase 1 seed, batch 1) · by:wilson-pruitt + claude ·date:2026-09-24 · change:availability checked and recorded · by:wilson-pruitt + claude ·
Parents
Weights descend
- fine_tuned_from → Llama 2 7B declared source Paper sec. 1: 'Llama 2-Chat, a fine-tuned version of Llama 2 that is optimized for dialogue use cases.'
Children
Weights descend
- ← fine_tuned_from Starling-RM-7B-alpha declared source Card: 'Starling-RM-7B-alpha is a reward model trained from Llama2-7B-Chat'; 'Finetuned from model: Llama2-7B-Chat'. Blog: 'Our reward model is fine-tuned from Llama2-7B-Chat'. The final layer is replaced by a scalar head, so weights below it descend.
Read in
No station on the reading path has touched this record yet.