| .. |
|
baby-llama
|
eb542d3932
Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384)
|
2 years ago |
|
benchmark
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
|
convert-llama2c-to-ggml
|
b19edd54d5
Adding support for llama2.c models (#2559)
|
2 years ago |
|
embd-input
|
ff966e7ca6
build : fix several cast and printf warnings (#2499)
|
2 years ago |
|
embedding
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
|
jeopardy
|
5ddf7ea1fb
hooks : setting up flake8 and pre-commit hooks (#1681)
|
2 years ago |
|
main
|
e59fcb2bc1
Add --n-predict -2 for stopping generation on full context (#2565)
|
2 years ago |
|
metal
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
|
perplexity
|
ff966e7ca6
build : fix several cast and printf warnings (#2499)
|
2 years ago |
|
quantize
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
|
quantize-stats
|
b1f4290953
cmake : install targets (#2256)
|
2 years ago |
|
save-load-state
|
65cdf34bdc
llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)
|
2 years ago |
|
server
|
10151bee2e
server : support for saving templates in browser LocalStorage (#2486)
|
2 years ago |
|
simple
|
ff966e7ca6
build : fix several cast and printf warnings (#2499)
|
2 years ago |
|
train-text-from-scratch
|
eb542d3932
Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384)
|
2 years ago |
|
CMakeLists.txt
|
b19edd54d5
Adding support for llama2.c models (#2559)
|
2 years ago |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
2 years ago |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
2 years ago |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
2 years ago |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
2 years ago |
|
chat-persistent.sh
|
1359b6aba5
chat-persistent.sh : use bracket expressions in grep (#1564)
|
2 years ago |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
2 years ago |
|
chat.sh
|
79b2b266db
If n_predict == -1, generate forever
|
2 years ago |
|
common.cpp
|
8dae7ce684
Add --cfg-negative-prompt-file option for examples (#2591)
|
2 years ago |
|
common.h
|
3498588e0f
Add --simple-io option for subprocesses and break out console.h and cpp (#1558)
|
2 years ago |
|
console.cpp
|
9ca4abed89
Handle `ENABLE_VIRTUAL_TERMINAL_PROCESSING` more gracefully on earlier versions of Windows.
|
2 years ago |
|
console.h
|
3498588e0f
Add --simple-io option for subprocesses and break out console.h and cpp (#1558)
|
2 years ago |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
2 years ago |
|
grammar-parser.cpp
|
ff966e7ca6
build : fix several cast and printf warnings (#2499)
|
2 years ago |
|
grammar-parser.h
|
84e09a7d8b
llama : add grammar-based sampling (#1773)
|
2 years ago |
|
json-schema-to-grammar.py
|
8183159cf3
examples : generate JSON according to schema (#1887)
|
2 years ago |
|
llama.vim
|
2d7baaf50f
vim : streaming and more (#2495)
|
2 years ago |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 years ago |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
2 years ago |
|
llm.vim
|
7ed8d1fe7f
llm.vim : multiline autocompletion, get rid of "^@" (#2543)
|
2 years ago |
|
make-ggml.py
|
7d5f18468c
examples : add easy python script to create quantized (k-bit support) GGML models from local HF Transformer models (#2311)
|
2 years ago |
|
reason-act.sh
|
a6956b25a1
add example of re-act pattern (#583)
|
2 years ago |
|
server-llama2-13B.sh
|
d73b8d48b4
examples : fix whitespace
|
2 years ago |
staviq
10151bee2e
server : support for saving templates in browser LocalStorage (#2486)