Resources

View closed (2)

W8A8 Quantization leads to wrong token

#31 opened 11 days ago by

opter

The model frequently refused to call tool

#28 opened 24 days ago by

O-delicious

tool_call streaming returns no `arguments`, which is not compatible with langchain framework

#27 opened 29 days ago by

LeonLiao

cerebras outputting <think>

#26 opened about 1 month ago by

therealkenc

🚀[Fine-tuning] 8x80GiB GPUs LoRA finetuning Qwen3-235B-A22B-Instruct-2507

🤗 4

#25 opened about 1 month ago by

study-hjt

🚀 Evaluation Best Practice !

👍 4

#24 opened about 1 month ago by

Yunxz

int4 and awq version

#23 opened about 1 month ago by

devops724

Tokenizer template is wrong?

#22 opened about 1 month ago by

eugenhotaj-ppl

Update README.md

#21 opened about 1 month ago by

EtherAI

Update README.md

#20 opened about 1 month ago by

csabakecskemeti

download on kaggle

#19 opened about 1 month ago by

malik33

An interesting phenomenon

#18 opened about 1 month ago by

Shuaiqi

Can this Run on 5090 64gb ram and 9950x3d

#17 opened about 1 month ago by

GrimReaper000

Good idea to remove the hybrid thinking mode

👍 4

#16 opened about 1 month ago by

rtzurtz

Why not introduce the 235b-2507 inference model

#15 opened about 1 month ago by

xldistance

What is GPT-4o-0327?

#14 opened about 1 month ago by

zml24

Jinja template fails on llama.cpp and has think tags for non-thinking model

#13 opened about 1 month ago by

sirus

Smaller models update?

➕ 👍 12

#12 opened about 1 month ago by

snapo

Failed to do function calling by qwe-3-235b-a22b-2507 provided by openrouter

#11 opened about 1 month ago by

LucyU2001

Does this version support yarn context extension?

#10 opened about 1 month ago by

rentianyue

4 bit quantisation release?

➕ 9

#9 opened about 1 month ago by

mochiyo

[Experiment] Confirmed by Arc Prize

#8 opened about 1 month ago by

clem

Just admit you train on the benchmark datasets

👍 👀 18

#7 opened about 1 month ago by

ChuckMcSneed

Review and Testing Video - Step by Step

#6 opened about 1 month ago by

fahdmirzac

Ensure Cerebras, Groq, and SambaNova support this.

➕ 6

#5 opened about 1 month ago by

AntDX316

SimpleQA jumped from 12.2 to 54.3?

🔥 🧠 22

#4 opened about 1 month ago by

phil111

Update README.md to fix invalid yaml

👍 1

#3 opened about 1 month ago by

neilmehta24

Base model

➕ 11

#2 opened about 1 month ago by

NyxKrage

Small Models

👍 19

#1 opened about 1 month ago by

PSM24