Stas Veretennikov PRO

ironbcc's activity

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

New activity in LocalLLaMA/typed-decisions 1 day ago

Seb-9B (9B, fitted on train, one question per request): 0.754 acc / KL 0.349 / Brier 0.131 / ECE 0.031 on the official test split

🚀 1

#13 opened 1 day ago by

ironbcc

New activity in autotrust/JEV-27B-VL 1 day ago

Seb-9B vs JEV-27B-VL on identical rows: 17 Laya public suites, a 6,920-row decision suite and two image suites (self-run)

#4 opened 1 day ago by

ironbcc

New activity in convaiinnovations/laya 1 day ago

Seb-9B vs Jev 1.13 vs Laya on the 17 public suites from Laya's benchmark report (identical questions, self-run)

#30 opened 1 day ago by

ironbcc

New activity in autotrust/JEV-27B-VL 1 day ago

Why no mlx inference support for decision models like this?

2

#3 opened 3 days ago by

Narutoouz

Feature Request: JEV-4B-VL — 12GB VRAM Multimodal Decision Model

🤝 1

4

#2 opened 6 days ago by

Exo87

New activity in jaredpalmer/kev-9b 1 day ago

use cases

1

#1 opened 16 days ago by

repla73

New activity in convaiinnovations/laya 1 day ago

Independent Laya vs Jev head-to-head on identical inputs

👍🔥 3

6

#6 opened 17 days ago by

saidutta69

A small real-world calibration check on Laya typed-decisions

1

#13 opened 15 days ago by

NambiarONS

New activity in Cloudflare/clef-flash 1 day ago

Support / Roadmap for serving Clef-Flash via vLLM?

🔥 1

1

#3 opened 2 days ago by

Vishva007

New activity in Qwen/Qwen3-Embedding-4B 2 months ago

How to set MRL (variable dimensions) in vLLM

❤️ 1

5

#21 opened 11 months ago by

janreges3

Qwen_quantized_dynamic_8-bit _(INT8)

1

#14 opened over 1 year ago by

Colegero

Anyone up for making a FP8 for 4B embedding and reranker?

1

#25 opened 7 months ago by

huggyfaceenjoyer