Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Tags: swordow/llama-cpp-python

Tags

main_joker_v0.3.7

Toggle main_joker_v0.3.7's commit message

Verified

This commit was signed with the committer’s verified signature.
swordow
GPG key ID: 49E0E424244A01DC
Verified
Learn about vigilant mode 
mod: 1. exports llama-embedding as dll using llama_batch_decode from …

…llama-embedding 2.create_embedding function adds normalize parameter for embedding normalization 3. Llama supports apply_chat_format 4. logits_all does not necessary be related with pooling type, sets True for all tokens in embed and be consistent with logic in llama-embedding.

v0.3.7

Toggle v0.3.7's commit message 
chore: Bump version

v0.3.6

Toggle v0.3.6's commit message 
chore: Bump version

v0.3.5

Toggle v0.3.5's commit message 
chore: Bump version

v0.3.5-metal

Toggle v0.3.5-metal's commit message 
chore: Bump version

v0.3.4

Toggle v0.3.4's commit message 
chore: Bump version

v0.3.4-metal

Toggle v0.3.4-metal's commit message 
chore: Bump version

v0.3.4-cu124

Toggle v0.3.4-cu124's commit message 
fix(ci): update macos runner image to non-deprecated version

v0.3.4-cu123

Toggle v0.3.4-cu123's commit message 
fix(ci): update macos runner image to non-deprecated version

v0.3.4-cu122

Toggle v0.3.4-cu122's commit message 
fix(ci): update macos runner image to non-deprecated version