riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 11:11:05 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

[docs] Fix mistral link in mixtral.md (#28143)

Browse Source 
Fix mistral link in mixtral.md
This commit is contained in:
Aaron Jimenez 2023-12-19 10:34:14 -08:00 committed by GitHub
parent 23f8e4db77
commit 38611086d2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/mixtral.md
View File

@ -42,7 +42,7 @@ Mixtral-45B is a decoder-based LM with the following architectural choices:
* Mixtral is a Mixture of Expert (MOE) model with 8 experts per MLP, with a total of 45B paramateres but the compute required is the same as a 14B model. This is because even though each experts have to be loaded in RAM (70B like ram requirement) each token from the hidden states are dipatched twice (top 2 routing) and thus the compute (the operation required at each foward computation) is just 2 X sequence_length.
The following implementation details are shared with Mistral AI's first model [mistral](~models/doc/mistral):
The following implementation details are shared with Mistral AI's first model [mistral](mistral):
* Sliding Window Attention - Trained with 8k context length and fixed cache size, with a theoretical attention span of 128K tokens
* GQA (Grouped Query Attention) - allowing faster inference and lower cache size.
* Byte-fallback BPE tokenizer - ensures that characters are never mapped to out of vocabulary tokens.