Model frequently hallucinates when answering a question written in non-English.
#45 opened 12 days ago
by
devopsML

Update README.md
#44 opened 30 days ago
by
Rizki-firman

Create chatsetup.py
#43 opened about 2 months ago
by
Raiff1982

申请发布awq格式模型:deepseek-ai/DeepSeek-R1-Distill-Qwen-32B-AWQ
#42 opened 2 months ago
by
classdemo
scsdifyonlie
#41 opened 2 months ago
by
ggsunny
Update README.md
#40 opened 2 months ago
by
nottii
Update README.md
#39 opened 2 months ago
by
nottii
Request: DOI
#38 opened 2 months ago
by
dragos-bajenaru37
[RESOLVED] Model is not outputting the <think> token at the beginning.
5
#37 opened 2 months ago
by
bsvaz
🚩 Report
1
#36 opened 2 months ago
by
proudcats

Generate crashed by repeatedly generating <think>
1
#35 opened 2 months ago
by
qpz
Weird......Dose it 32b model support vision ability ?
#34 opened 3 months ago
by
baiall

Set base_model to deepseek-ai/DeepSeek-R1
#33 opened 3 months ago
by
victor

How to build tools call system prompt?
1
#32 opened 3 months ago
by
zhaocc1106
The input starts with the token "<|begin▁of▁sentence|>" repeated twice. / 输入开头重复2次“<|begin▁of▁sentence|>”
#31 opened 3 months ago
by
Gya123
Can you distill qwen-2.5-72b?
1
1
#30 opened 3 months ago
by
xldistance
weight files naming is not regular rule
#29 opened 3 months ago
by
haili-tian
bos_token_id is defined incorrectly
1
#28 opened 3 months ago
by
haili-tian
Longer context length
2
#26 opened 3 months ago
by
comorado
Qwen 32B Compatibility on PC w/ Ryzen 7 Pro 8840HS w/ 780M Graphics 2x32GB RAM 1TB DDR5 SSD
#25 opened 3 months ago
by
arzx
请问我在用llama-factory微调distill-qwen系列模型时,模型名称选哪个?
1
#24 opened 3 months ago
by
wangda1
Update README.md
#23 opened 3 months ago
by
Rizki-firman

Update README.md
#22 opened 3 months ago
by
payam8499
Tokenizer config's `chat_template` removes everything before `</think>` XML closing tag
3
2
#21 opened 3 months ago
by
jamesbraza

Consistency, can Deepseek pass? 一致性,deepseek能及格吗?
#20 opened 3 months ago
by
zwpython

running on local machine
7
#19 opened 3 months ago
by
saidavanam
Poor performance in the leaderboard?
1
7
#17 opened 3 months ago
by
L29Ah
Add text-generation pipeline tag
#16 opened 3 months ago
by
nielsr

comfyui-deepseek-r1
3
#15 opened 3 months ago
by
zwpython

sharing something maybe beneficial ?
#13 opened 3 months ago
by
9x25dillon

Please convert these models to GGUF format...
2
5
#12 opened 3 months ago
by
Moodym
Support For Japanese Model
2
5
#11 opened 3 months ago
by
alfredplpl

Tokenizer config is wrong
8
#10 opened 3 months ago
by
stoshniwal
Garbage characters generated with using 32B
3
#9 opened 3 months ago
by
carlosbdw
Please add a qwen2.5-72b distill
21
#8 opened 3 months ago
by
warlock-edward
Does this have tooling support?
8
4
#7 opened 3 months ago
by
xceptor

What temp are these expected to be used at?
2
#6 opened 3 months ago
by
rombodawg

YaRN block required?
3
#5 opened 3 months ago
by
robbiemu
Please add a qwen coder 32b distill.
19
#4 opened 3 months ago
by
ciprianv
System Prompt
16
18
#2 opened 3 months ago
by
Wanfq
