Resources

View closed (10)

vLLM MoE Config

#32 opened 1 day ago by

j4ys0n

We Need 70B Model!!,

🚀 2

#31 opened 10 days ago by

gigascake

SWE-bench Verified Repro

#30 opened 14 days ago by

vim-ary

What does `max_window_layers` do?

#29 opened about 1 month ago by

jonaskuebler

Update chat_template.jinja

#28 opened about 1 month ago by

mahmoudhas9

rQwen25Sep

#27 opened about 1 month ago by

bigfundu

Add `{% generation %} to support tokenizer.apply_chat_template return_assistant_tokens_mask

#25 opened about 2 months ago by

zeromquan

在python 3.7中运行模板需要将|items改为.items()

#23 opened 2 months ago by

bloomv

Tool Call parser not working in vLLM

#19 opened 3 months ago by

VivekMalipatel23

Is AWQ quantization possible for this model?

👀 1

#17 opened 3 months ago by

VivekMalipatel23

attention_bias error

#16 opened 3 months ago by

capyun

Update Jinja template for Jinja version compatibility

#13 opened 3 months ago by

rshcao

How to achieve reliable native function calling

👍 4

#12 opened 3 months ago by

Ithanil

what does `shared_expert_intermediate_size` in the config for?

👀 1

#11 opened 3 months ago by

Viper403

Base model

👍 2

#9 opened 3 months ago by

Mokanarangan

LoRA adapters?

➕ 4

#8 opened 3 months ago by

lightenup

Update README.md

#7 opened 3 months ago by

Fernanda24

typo in README.md

#6 opened 3 months ago by

Fernanda24

Local Installation Video with Ollama and Testing - Step by Step

#5 opened 3 months ago by

fahdmirzac

Best snake game in html ever :)

❤️ 4

#4 opened 3 months ago by

urtuuuu

FIM completion

👍 3

#2 opened 3 months ago by

dr-e

Update README.md

#1 opened 3 months ago by

snapo