llama.cpp
Fix import of llama2.c models that don't share weights between embedding layers
#2685
Merged

Fix import of llama2.c models that don't share weights between embedding layers #2685

ochafik
byte-6174
karpathy
byte-6174
ochafik
byte-6174
ochafik
ochafik
ochafik
byte-6174
ggerganov
ggerganov approved these changes on 2023-08-21
ochafik
byte-6174
byte-6174
byte-6174
ochafik
Fix import of llama2.c models that don't share weights between embedd…
0f7cb953
ochafik ochafik force pushed from 480feb89 to 0f7cb953 2 years ago
ochafik
klosax
klosax
byte-6174
byte-6174
byte-6174
ggerganov
ggerganov approved these changes on 2023-08-22
ggerganov
klosax
byte-6174
byte-6174
klosax
klosax
ggerganov
byte-6174
klosax
byte-6174
ochafik
llama2c: reinstate ggmlv3 conversion output + update readme w/ gguf conv
59f67c69
ochafik
byte-6174
ochafik
llama2.c: comment out legacy "load from ggml model" logic
8ad1e2d8
ochafik
byte-6174
ochafik
byte-6174
byte-6174
byte-6174
ochafik
ochafik
byte-6174
ochafik
byte-6174
llama2.c: convert special-cased "<0xXX>" single byte tokens from toke…
8d0dc476
ochafik
ggerganov
ggerganov approved these changes on 2023-08-23
ggerganov ggerganov merged 95385241 into master 2 years ago
ochafik

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone