Mixtral-8x22B-Instruct-v0.1 config.json

Fields

id

sources/model-fr-hf-config-mixtral-8x22b

URL

https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1/raw/main/config.json

Publisher

Hugging Face (Mistral AI)

Kind

repo

Published

2024-04-17

Accessed

2026-10-03

notes

hidden 6144, 56 layers, 48 q heads, 8 kv heads, intermediate 16384, 8 local experts, 2 per token, max_position_embeddings 65536, vocab 32000. | SOURCE AUDIT 2026-10-03: kind was 'spec-sheet' but the URL is a raw Hugging Face config.json served as text/plain, not a vendor spec sheet; set to 'repo'. The schema field it fills (layer/window/head counts) is machine-readable model metadata and should be read as such.

Notes

hidden 6144, 56 layers, 48 q heads, 8 kv heads, intermediate 16384, 8 local experts, 2 per token, max_position_embeddings 65536, vocab 32000. | SOURCE AUDIT 2026-10-03: kind was 'spec-sheet' but the URL is a raw Hugging Face config.json served as text/plain, not a vendor spec sheet; set to 'repo'. The schema field it fills (layer/window/head counts) is machine-readable model metadata and should be read as such.

Cross-references

This record references no other records.