| .. |
|
baby-llama
|
ab336a9d5e
code : normalize enum names (#5697)
|
vor 1 Jahr |
|
batched
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
batched-bench
|
87e21bbacd
bench : make n_batch and n_ubatch configurable in Batched bench (#6500)
|
vor 1 Jahr |
|
batched.swift
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
vor 1 Jahr |
|
beam-search
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
benchmark
|
5b09797321
ggml : remove old quantization functions (#5942)
|
vor 1 Jahr |
|
convert-llama2c-to-ggml
|
2ab4f00d25
llama2c : open file as binary (#6332)
|
vor 1 Jahr |
|
embedding
|
1b67731e18
BERT tokenizer fixes (#6498)
|
vor 1 Jahr |
|
eval-callback
|
4bd0f93e4a
model: support arch `DbrxForCausalLM` (#6515)
|
vor 1 Jahr |
|
export-lora
|
6e4e973b26
ci : add an option to fail on compile warning (#3952)
|
vor 1 Jahr |
|
finetune
|
ab336a9d5e
code : normalize enum names (#5697)
|
vor 1 Jahr |
|
gbnf-validator
|
cbaadc9294
grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses) (#6609)
|
vor 1 Jahr |
|
gguf
|
8228b66dbc
gguf : add option to not check tensor data (#6582)
|
vor 1 Jahr |
|
gguf-split
|
8800226d65
Fix --split-max-size (#6655)
|
vor 1 Jahr |
|
gritlm
|
8a56075b07
gritlm : add --outdir option to hf.sh script (#6699)
|
vor 1 Jahr |
|
imatrix
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
vor 1 Jahr |
|
infill
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
jeopardy
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
vor 2 Jahren |
|
llama-bench
|
8cc91dc63c
ggml : add llamafile sgemm (#6414)
|
vor 1 Jahr |
|
llama.android
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
llama.swiftui
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
vor 1 Jahr |
|
llava
|
89b0bf0d5d
llava : use logger in llava-cli (#6797)
|
vor 1 Jahr |
|
lookahead
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
lookup
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
vor 1 Jahr |
|
main
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
vor 1 Jahr |
|
main-cmake-pkg
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
vor 1 Jahr |
|
parallel
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
passkey
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
perplexity
|
58227ffdeb
perplexity : require positive --ctx-size arg (#6695)
|
vor 1 Jahr |
|
quantize
|
5c4d767ac0
chore: Fix markdown warnings (#6625)
|
vor 1 Jahr |
|
quantize-stats
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
vor 1 Jahr |
|
retrieval
|
64e7b47c69
examples : add "retrieval" (#6193)
|
vor 1 Jahr |
|
save-load-state
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
vor 1 Jahr |
|
server
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
vor 1 Jahr |
|
simple
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
speculative
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
vor 1 Jahr |
|
sycl
|
de17e3f745
fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)
|
vor 1 Jahr |
|
tokenize
|
1b67731e18
BERT tokenizer fixes (#6498)
|
vor 1 Jahr |
|
train-text-from-scratch
|
8b1b1f4982
train : add general name (#6752)
|
vor 1 Jahr |
|
CMakeLists.txt
|
b804b1ef77
eval-callback: Example how to use eval callback for debugging (#6576)
|
vor 1 Jahr |
|
Miku.sh
|
019fe257bb
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
|
vor 2 Jahren |
|
alpaca.sh
|
a17a2683d8
alpaca.sh : update model file name (#2074)
|
vor 2 Jahren |
|
base-translate.sh
|
96e80dabc6
examples : improve base-translate.sh script (#4783)
|
vor 2 Jahren |
|
chat-13B.bat
|
d9ad104440
Create chat-13B.bat (#592)
|
vor 2 Jahren |
|
chat-13B.sh
|
6daa09d879
examples : read chat prompts from a template file (#1196)
|
vor 2 Jahren |
|
chat-persistent.sh
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
vor 2 Jahren |
|
chat-vicuna.sh
|
c36e81da62
examples : add chat-vicuna.sh (#1854)
|
vor 2 Jahren |
|
chat.sh
|
8341a25957
main : log file (#2748)
|
vor 2 Jahren |
|
gpt4all.sh
|
107980d970
examples : add -n to alpaca and gpt4all scripts (#706)
|
vor 2 Jahren |
|
json-schema-pydantic-example.py
|
5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
|
vor 1 Jahr |
|
json_schema_to_grammar.py
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
vor 1 Jahr |
|
llama.vim
|
125d03a503
llama.vim : added api key support (#5090)
|
vor 2 Jahren |
|
llama2-13b.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
vor 2 Jahren |
|
llama2.sh
|
73643f5fb1
gitignore : changes for Poetry users + chat examples (#2284)
|
vor 2 Jahren |
|
llm.vim
|
ad9ddcff6e
llm.vim : stop generation at multiple linebreaks, bind to <F2> (#2879)
|
vor 2 Jahren |
|
make-ggml.py
|
ac43576124
make-ggml.py : compatibility with more models and GGUF (#3290)
|
vor 2 Jahren |
|
pydantic-models-to-grammar-examples.py
|
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099)
|
vor 2 Jahren |
|
pydantic_models_to_grammar.py
|
d292f4f204
examples : make pydantic scripts pass mypy and support py3.8 (#5099)
|
vor 2 Jahren |
|
reason-act.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
vor 2 Jahren |
|
regex-to-grammar.py
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
vor 1 Jahr |
|
server-embd.py
|
2002bc96bf
server : refactor (#5882)
|
vor 1 Jahr |
|
server-llama2-13B.sh
|
7c2227a197
chmod : make scripts executable (#2675)
|
vor 2 Jahren |
|
ts-type-to-grammar.sh
|
ab9a3240a9
JSON schema conversion: ⚡️ faster repetitions, min/maxLength for strings, cap number length (#6555)
|
vor 1 Jahr |
Johannes Gäßler
28103f4832
Server: fix seed for multiple slots (#6835)