Model · wizardlm-13b-v1-2
WizardLM-13B-V1.2
Developer: WizardLM Team (Microsoft Research collaboration)
Availability: available · checked 2026-09-24 · source
Raw record: /data/models/wizardlm-13b-v1-2.json
Fields
- id
- wizardlm-13b-v1-2
- identifiers
- huggingface
- WizardLMTeam/WizardLM-13B-V1.2
- developer
- WizardLM Team (Microsoft Research collaboration)
- release_date
- 2023-07-25partial · sourcenote: HF repo creation date; may predate or postdate public release.
- weights_status
- open
- availability
- available · checked 2026-09-24 · source
- license
- llama2partial · sourcenote: From HF card metadata (uploader-declared); confirm against the license text.
- architecture
- family
- decoder_only
- note
- family read from config 'architectures': ['LlamaForCausalLM'].
- n_layers
- 40recorded · source
- hidden_size
- 5120recorded · source
- n_heads
- 40recorded · source
- vocab_size
- 32000recorded · source
- context_length
- 4096recorded · source
- n_kv_heads
- 40recorded · source
- positional_encoding
- nullnot_recorded
- training_data
- Evol-Instruct: instructions iteratively rewritten/elaborated by an LLM from a seed instruction set, per the WizardLM paper series. No single resolvable dataset id.partial · sourcenote: Checked 2026-09-24: the V1.2 card names no training data. The evol-instruct-70k card says only 'This is the training data of WizardLM' (the paper's original model). No source found tying V1.2 to it, so no trained_on edge is recorded.
- techniques
- instruction-tuningevol-instruct
- primary_sources
- record_history
- date:2026-09-24 · change:ingested as candidate from HF (WizardLMTeam/WizardLM-13B-V1.2@cf5f40382559f19e13874e45b39575171ca46ef8) · by:ingest_hf.py ·date:2026-09-24 · change:preparer: developer, fine_tuned_from llama-2-13b added · 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:preparer cleanup: training_data filled · by:claude (preparer, Sonnet 5) ·date:2026-09-24 · change:reviewed and promoted from staging (1 edge(s) accepted) · by:Wilson Pruitt ·date:2026-09-24 · change:checked for an Evol-Instruct trained_on edge; none sourced, note added to training_data · by:wilson-pruitt + claude ·
Parents
Weights descend
- fine_tuned_from → Llama-2-13b-hf declared_by_uploader source Card: 'this model is trained from Llama-2 13b'.
Children
No edges recorded.
Read in
No station on the reading path has touched this record yet.