cpral PRO

cpral's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper about 1 month ago

NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs

Paper • 2607.14186 • Published about 1 month ago • 18 •

4

New activity in Goldkoron/Qwen3.5-397B-A17B 3 months ago

Can you share KLD sensitivity data measurement scripts?

2

#4 opened 3 months ago by

cpral

New activity in nex-agi/Nex-N2-Pro 3 months ago

Mid-training and post-training SFT dataset size

#9 opened 3 months ago by

cpral

What a Monster. It is very good...

🔥 3

23

#5 opened 3 months ago by

Hunterx

New activity in mratsim/Qwen3.5-397B-A17B-EXL3 4 months ago

model tag was copied from GLM 4.7 quant and it points to GLM 4.7 being the base model

2

#2 opened 4 months ago by

cpral

New activity in mratsim/GLM-4.7-EXL3 4 months ago

KLD sample size

2

#8 opened 4 months ago by

cpral

New activity in mratsim/Qwen3.5-397B-A17B-EXL3 4 months ago

Can you upload 8bpw quant too?

1

#1 opened 4 months ago by

cpral

New activity in MikeRoz/Qwen3.5-397B-A17B-exl3 5 months ago

2.08bpw quant has awesome KLD and PPL

#1 opened 5 months ago by

cpral