5 Commits

Author	SHA1	Message	Date
Jared Van Bortel	be66ec8ab5	chat: faster KV shift, continue generating, fix stop sequences (#2781) ... * Don't stop generating at end of context * Use llama_kv_cache ops to shift context * Fix and improve reverse prompt detection * Replace prompt recalc callback with a flag to disallow context shift	2024-08-07 11:25:24 -04:00
Jared Van Bortel	51bd01ae05	backend: fix extra spaces in tokenization and a CUDA crash (#2778) ... Also potentially improves accuracy of BOS insertion, token cache, and logit indexing. Signed-off-by: Jared Van Bortel <jared@nomic.ai>	2024-08-01 10:46:36 -04:00
Jared Van Bortel	41c9013fa4	chat: don't use incomplete types with signals/slots/Q_INVOKABLE (#2408) ... Signed-off-by: Jared Van Bortel <jared@nomic.ai>	2024-06-06 11:59:28 -04:00
Jared Van Bortel	d3d777bc51	chat: fix #includes with include-what-you-use (#2401) ... Also use qGuiApp instead of qApp. Signed-off-by: Jared Van Bortel <jared@nomic.ai>	2024-06-04 14:47:11 -04:00
Olyxz16	2c0a660e6e	feat: Add support for Mistral API models (#2053) ... Signed-off-by: Jared Van Bortel <jared@nomic.ai> Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com> Co-authored-by: Jared Van Bortel <jared@nomic.ai>	2024-03-13 18:23:57 -04:00