summaryrefslogtreecommitdiff
path: root/candle-transformers/src/models/mistral.rs
Commit message (Expand)AuthorAgeFilesLines
* Add Pixtral. (#2521)Laurent Mazare2024-09-301-4/+34
* Support for mistral-nemo. (#2396)Laurent Mazare2024-08-041-5/+12
* Use cat for faster MQA computation. (#2043)Laurent Mazare2024-04-121-14/+2
* Use the new rope kernel in mistral. (#1937)Laurent Mazare2024-03-251-14/+6
* Support more mistral models. (#1927)Laurent Mazare2024-03-241-20/+26
* Avoid broadcasting on the batch dimension for the attention mask. (#1920)Laurent Mazare2024-03-231-4/+3
* Use a common with_tracing::RmsNorm in a few models. (#1871)Jani Monoses2024-03-181-22/+1
* add config_amazon_mistral_lite (#1493)Daniel Clough2023-12-281-0/+18
* feat: add clear_kv_cache to mistral and qmistral models (#1464)drbh2023-12-211-0/+14
* make fn name generic (#1459)Daniel Clough2023-12-211-1/+2
* add fn config_chat_ml (#1458)Daniel Clough2023-12-201-0/+19
* Make some model cloneable. (#1125)Laurent Mazare2023-10-181-6/+6
* Quantized version of mistral. (#1009)Laurent Mazare2023-09-301-12/+12
* Use flash-attn for mistral. (#1004)Laurent Mazare2023-09-301-8/+37
* Use a silu activation in mistral. (#991)Laurent Mazare2023-09-291-1/+1
* Add the sliding window. (#986)Laurent Mazare2023-09-281-2/+9
* Mistral gpu fix (#985)Laurent Mazare2023-09-281-5/+8
* Add the mistral example. (#984)Laurent Mazare2023-09-281-11/+14
* Add the Mistral 7b model (#983)Laurent Mazare2023-09-281-0/+364
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-05 02:05:32 +0000