Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

merge from upstream #7

Merged
merged 48 commits into from
Apr 6, 2024
Merged
Changes from 1 commit
Commits
Show all changes
48 commits
Select commit Hold shift + click to select a range
be55134
convert : refactor vocab selection logic (#6355)
cebtenzzre Mar 28, 2024
5106ef4
[SYCL] Revisited & updated SYCL build documentation (#6141)
OuadiElfarouki Mar 28, 2024
bfe7daf
readme : add notice for UI list
ggerganov Mar 28, 2024
b75c381
convert : allow conversion of Mistral HF models (#6144)
pcuenca Mar 29, 2024
057400a
llama : remove redundant reshape in build_kv_store (#6369)
danbev Mar 29, 2024
8093987
cmake : add explicit metal version options (#6370)
mattjcly Mar 29, 2024
b910287
readme : add project (#6356)
zhouwg Mar 29, 2024
cfde806
ci : fix BGE wget (#6383)
ggerganov Mar 29, 2024
0695747
[Model] Add support for xverse (#6301)
hxer7963 Mar 29, 2024
d48ccf3
sync : ggml (#6351)
ggerganov Mar 29, 2024
ba0c7c7
Vulkan k-quant mmq and ggml-backend offload functionality (#6155)
0cc4m Mar 29, 2024
f7fc5f6
split: allow --split-max-size option (#6343)
ngxson Mar 29, 2024
c342d07
Fedora build update (#6388)
Man2Dev Mar 29, 2024
37e7854
ci: bench: fix Resource not accessible by integration on PR event (#6…
phymbert Mar 30, 2024
c50a82c
readme : update hot topics
ggerganov Mar 31, 2024
226e819
ci: server: verify deps are coherent with the commit (#6409)
phymbert Apr 1, 2024
33a5244
compare-llama-bench.py: fix long hexsha args (#6424)
JohannesGaessler Apr 1, 2024
f87f7b8
flake.lock: Update (#6402)
ggerganov Apr 1, 2024
5260486
[SYCL] Disable iqx on windows as WA (#6435)
airMeng Apr 3, 2024
08a0c02
ggml : mul_mat_id use the same tensor for all the experts (#6387)
slaren Apr 3, 2024
076b086
readme : update hot topics
ggerganov Apr 3, 2024
1ff4d9f
Add OpenChat, Alpaca, Vicuna chat templates (#6397)
kaizau Apr 3, 2024
db214fa
Missing tokenizer.model error during gguf conversion (#6443)
overtunned Apr 3, 2024
e69945d
security : create policy (#6354)
joycebrum Apr 3, 2024
154d4ee
readme : add feature-rich rust bindings (#6465)
francis2tm Apr 3, 2024
5d4f12e
server: add cURL support to `server.Dockerfile` (#6461)
elepedus Apr 3, 2024
9f62c01
ci : update checkout, setup-python and upload-artifact to latest (#6456)
EwoutH Apr 3, 2024
bb43cf7
llama : add SEA-LION support (#6448)
bryanSwk Apr 3, 2024
60cdf40
server : handle exception on wrong type in request (#6452)
JH23X Apr 3, 2024
5fb1574
A few small fixes to server's README docs (#6428)
fat-tire Apr 3, 2024
72d73af
convert : fix for lint error complaining of bare except (#6470)
HanClinto Apr 4, 2024
1a43c72
server : add option to disable KV offload (#6468)
jxy Apr 4, 2024
4399f13
server : remove obsolete --memory-f32 option
ggerganov Apr 4, 2024
9b84ae1
examples : add GBNF validator program (#5948)
HanClinto Apr 4, 2024
4bcd6b9
common: remove duplicate check for curl (#6471)
danbev Apr 4, 2024
7a2c926
ci: bench: add more ftype, fix triggers and bot comment (#6466)
phymbert Apr 4, 2024
a74401f
Correct README link (#6458)
limitedAtonement Apr 4, 2024
8120efe
ci: bench fix concurrency for workflow trigger dispatch with sha1 (#6…
phymbert Apr 4, 2024
2e66913
server: allow penalizing repetition of newlines on server webpage (#6…
sha224 Apr 4, 2024
c666ba2
build CI: Name artifacts (#6482)
EwoutH Apr 4, 2024
7dda1b7
ci: exempt master branch workflows from getting cancelled (#6486)
mscheong01 Apr 4, 2024
0a1d889
server: add cURL support to server Dockerfiles (#6474)
elepedus Apr 4, 2024
b660a57
readme : fix typo (#6481)
junnjiee Apr 4, 2024
a307375
readme : add Dot to UI list (#6487)
alexpinel Apr 4, 2024
1b496a7
[SYCL] Fixed minor bug when enabling FP16 for non intel targets (#6464)
OuadiElfarouki Apr 5, 2024
87e21bb
bench : make n_batch and n_ubatch configurable in Batched bench (#6500)
Sunt-ing Apr 5, 2024
d0f5dee
readme : update UI list (#6503)
hugo53 Apr 5, 2024
a8bd14d
gguf.py : add licence and version to gguf writer (#6504)
mofosyne Apr 5, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
convert : fix for lint error complaining of bare except (ggml-org#6470)
HanClinto authored Apr 4, 2024
commit 72d73af65132792a52433952ca4729b01c36cde2
3 changes: 2 additions & 1 deletion convert-hf-to-gguf.py
Original file line number Diff line number Diff line change
@@ -513,7 +513,8 @@ class MPTModel(Model):
def set_vocab(self):
try:
self._set_vocab_gpt2()
except:
except Exception:
# Fallback for SEA-LION model
self._set_vocab_sentencepiece()
self.gguf_writer.add_add_bos_token(False)
self.gguf_writer.add_pad_token_id(3)