Spaces:
Sleeping
Sleeping
Commit History
talk-llama : reject runs without required arguments (#2153)
b445508
unverified
talk-llama : sync llama.cpp
f5f68d6
talk-llama : use llama_decode instead of llama_eval
301b000
unverified
talk, talk-llama : pass text_to_speak as a file (#1865)
3fd8b4d
unverified
Tamotsu Takahashi
commited on
talk-llama : sync llama.cpp
542accf
unverified
examples : initialize context params properly (#1852)
3443ee7
unverified
talk-llama : stream response (#1121)
2193f2b
unverified
talk-llama : optional wake-up command and audio confirmation (#1765)
542e8da
unverified
talk-llama : add optional CLI arg to set the bot name (#1764)
63c8089
unverified
RhinoDevel
commited on
sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
aa86ade
unverified
talk-llama : improve quote and backtick handling (#1364)
fa6a8a8
unverified
Sam Pullara
commited on
talk-llama : enable GPU by default
afd6523
unverified
talk-llama : add n_gpu_layers parameter (#1475)
aa7c2e9
unverified
talk-llama : add language auto detect (#1467)
cfc50d3
unverified
talk-llama : fix n_gpu_layers usage again (#1442)
37d6862
unverified
examples : fix n_gpu_layers usage in talk-llama (#1441)
e0ea7d1
unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified
talk-llama : update to latest llama.cpp
1493d0c
unverified
build : do not use _GNU_SOURCE gratuitously (#1129)
beefa34
unverified
Przemysław Pawełczyk
commited on
examples : fix build + compile warnings (close #1256)
2cfc05a
unverified
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"
1e5ddb0
unverified
ggml : do not use _GNU_SOURCE gratuitously (#1027)
3a69cdf
unverified
Przemysław Pawełczyk
commited on
`speak` scripts for Windows
2fdd855
talk-llama : sync latest llama.cpp (close #922, close #954)
ad4065a
unverified
talk-llama : fix build + sync latest llama.cpp
ef85c02
unverified
talk-llama : fix session prompt load (#854)
6eca3b7
unverified
Luis Herrera
commited on
talk-llama : add --session support (#845)
a7b3aa5
unverified
Luis Herrera
commited on
whisper : add integer quantization support (#540)
a5f8f3c
unverified
talk-llama : correct default speak.sh path (#720)
d01a1c6
unverified
Maciek
commited on
talk-llama : increase context to 2048
adc4282
unverified
talk-llama : fixing usage message for talk-llama (#687)
2c3a469
unverified
InconsolableCellist
commited on
