tool calls sometimes fail on vllm
#19 opened 1 day ago
by
viktara
Not support flash_attn_2๏ผ
#17 opened 4 days ago
by
bdsqlsz
chatllm.cpp adds support of this model
๐
5
1
#16 opened 4 days ago
by
J22
possible bug in processing_step3.py?
2
#15 opened 4 days ago
by
J22
Quantisation support for this model
โค๏ธ
3
3
#14 opened 4 days ago
by
dineshananthi
Update processing_step3.py
#13 opened 5 days ago
by
jakubstrawa
Installation Video and Testing - Step by Step
๐
5
#12 opened 5 days ago
by
fahdmirzac
is it possible to provide FP8 version in additional to BF16
๐ฅ
8
1
#10 opened 6 days ago
by
water258
Incorrect eos_token_id in config causing infinite generation
1
#9 opened 7 days ago
by
WenyaLi
perfect
๐ค
14
#8 opened 7 days ago
by
ares2324
Doesn't work in OpenAI Streaming Interface
2
#7 opened 9 days ago
by
pytokusu
Add pipeline tag and library name to metadata
#6 opened 9 days ago
by
nielsr
vLLM is not working
9
#4 opened 10 days ago
by
wei01
Typo in paper
1
#3 opened 11 days ago
by
hgsg
Llama.cpp support
๐
๐ฅ
13
2
#2 opened 11 days ago
by
tcpmux
่ฏท้ฎๆๆจ่็ๅค็ฐ่ถ ๅๅ๏ผ
1
#1 opened 11 days ago
by
JjjjjZzz