| .. |
|
batched
|
267c1399f1
common : refactor downloading system, handle mmproj with -hf option (#12694)
|
hai 9 meses |
|
batched.swift
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
hai 4 meses |
|
convert-llama2c-to-ggml
|
a81283820a
gguf: gguf_writer refactor (#15691)
|
hai 4 meses |
|
deprecation-warning
|
f112d198cd
Update deprecation-warning.cpp (#10619)
|
hai 1 ano |
|
diffusion
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
hai 4 meses |
|
embedding
|
00131d6eaf
tests : update for LLAMA_SET_ROWS=1 (#14961)
|
hai 5 meses |
|
eval-callback
|
a8bca68f72
fix: Compute the full sum in llama-eval-callback, not just the sum of printed values (#15637)
|
hai 4 meses |
|
gen-docs
|
7cc2d2c889
ggml : move AMX to the CPU backend (#10570)
|
hai 1 ano |
|
gguf
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
hai 1 ano |
|
gguf-hash
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
hai 1 ano |
|
gritlm
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
hai 7 meses |
|
jeopardy
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
llama.android
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hai 7 meses |
|
llama.swiftui
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hai 7 meses |
|
lookahead
|
2f37014073
lookahead : add sample command to readme (#15447)
|
hai 4 meses |
|
lookup
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hai 7 meses |
|
model-conversion
|
5d6688de08
model-conversion : add --embeddings flag to modelcard.template [no ci] (#15801)
|
hai 4 meses |
|
parallel
|
2adf8d83ac
parallel : add option for different RNG seeds (#14757)
|
hai 6 meses |
|
passkey
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
hai 4 meses |
|
retrieval
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
hai 4 meses |
|
save-load-state
|
00131d6eaf
tests : update for LLAMA_SET_ROWS=1 (#14961)
|
hai 5 meses |
|
simple
|
9c55e5c5c2
fix: check model pointer validity before use (#13631)
|
hai 8 meses |
|
simple-chat
|
d7f5f4e578
simple-chat : fix context-exceeded condition (#14494)
|
hai 6 meses |
|
simple-cmake-pkg
|
68ff663a04
repo : update links to new url (#11886)
|
hai 11 meses |
|
speculative
|
e92d53b29e
sampling : optimize samplers by reusing bucket sort (#15665)
|
hai 4 meses |
|
speculative-simple
|
d8914fc47e
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters (#15191)
|
hai 5 meses |
|
sycl
|
29f538ac63
examples : remove references to `make` in examples [no ci] (#15457)
|
hai 4 meses |
|
training
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hai 5 meses |
|
CMakeLists.txt
|
2758fa10da
examples : add model conversion tool/example (#15455)
|
hai 4 meses |
|
Miku.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
%!s(int64=2) %!d(string=hai) anos |
|
chat-13B.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
chat-persistent.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
chat-vicuna.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
chat.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
convert_legacy_llama.py
|
a0ec17b32e
metadata: Detailed Dataset Authorship Metadata (#8875)
|
hai 1 ano |
|
json_schema_pydantic_example.py
|
3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
|
hai 1 ano |
|
json_schema_to_grammar.py
|
d5fe4e81bd
grammar : handle maxItems == 0 in JSON schema (#13117)
|
hai 8 meses |
|
llama.vim
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
hai 4 meses |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
%!s(int64=2) %!d(string=hai) anos |
|
pydantic_models_to_grammar.py
|
090fca7a07
pydantic : replace uses of __annotations__ with get_type_hints (#8474)
|
hai 1 ano |
|
pydantic_models_to_grammar_examples.py
|
1d36b3670b
llama : move end-user examples to tools directory (#13249)
|
hai 8 meses |
|
reason-act.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
regex_to_grammar.py
|
e235b267a2
py : switch to snake_case (#8305)
|
hai 1 ano |
|
server-llama2-13B.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
|
server_embd.py
|
a19b5cef16
llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)
|
hai 9 meses |
|
ts-type-to-grammar.sh
|
e9b6350e61
scripts : make the shell scripts cross-platform (#14341)
|
hai 6 meses |
Erik Scholz
a81283820a
gguf: gguf_writer refactor (#15691)