Timothy Rohrbaugh PRO

trohrbaugh's activity

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

New activity in trohrbaugh/Qwen3.8-Flash-Next-heretic-2 30 days ago

Please share the lora for trohrbaugh/Qwen3.8-Flash-Next-heretic-2

5

#1 opened about 1 month ago by

MJHAU

New activity in Qwen/Qwen3.8-27B about 1 month ago

Qwen 3.8 get stuck in massive 20k–50k token thinking loops on SGLang?

7

#178 opened 2 months ago by

undeadindustries

New activity in deepseek-ai/DeepSeek-V4.1-Flash about 2 months ago

DeepSeek V4.1 Flash Lite

➕👍 36

16

#11 opened about 2 months ago by

KeinNiemand

New activity in OBLITERATUS/Qwen3.8-27B-OBLITERATED about 2 months ago

`chat_template.jinja` differs from the base — plain API calls return empty `content`, and `reasoning_effort` is inert

#14 opened about 2 months ago by

trohrbaugh

New activity in trohrbaugh/Qwen3.8-27B-heretic-ara about 2 months ago

LORAs at lower KLD ?

1

#5 opened about 2 months ago by

DavidAU

New activity in trohrbaugh/Hy3-heretic 2 months ago

Hy3-FP8?

1

#2 opened 2 months ago by

AgileTurnip

New activity in trohrbaugh/Qwen3.8-27B-heretic-ara 2 months ago

Will it support dflash2?

1

#4 opened 2 months ago by

wanghf

NVFP4 Version

🔥 3

1

#3 opened 2 months ago by

PassingByPixels

This model is still fairly prone to refusals in thinking mode

2

#1 opened 3 months ago by

cchickk

https://github.com/timrohrbaugh/heretic gives 404

1

#2 opened 3 months ago by

trithemius

New activity in deepseek-ai/DeepSeek-V4-Flash-0731 3 months ago

How can it be served with 4 x RTX Pro6000?

👀 1

19

#22 opened 3 months ago by

niuchuang

New activity in RedHatAI/Inkling-Small-FP8-dynamic 3 months ago

This quant needs fixing

2

#1 opened 3 months ago by

trohrbaugh

New activity in trohrbaugh/Hy3-heretic 4 months ago

Can you create awq int 4 version?

1

#1 opened 4 months ago by

denisvasi

New activity in InternScience/Agents-A1 4 months ago

tool calling fail is an artifact of post training

#13 opened 4 months ago by

trohrbaugh

New activity in trohrbaugh/ZAYA1-74B-preview-heretic 6 months ago

IMO after trying it in VLLM with custom kernels

1

#1 opened 6 months ago by

coughmedicine

New activity in Zyphra/ZAYA1-74B-preview 6 months ago

Multi-GPU inference requires 6 patches to modeling_zaya.py

2

#2 opened 6 months ago by

trohrbaugh

New activity in trohrbaugh/Qwen3.6-27B-heretic-ara 6 months ago

Bug found

1

#2 opened 6 months ago by

trohrbaugh

could you make an uncensored version of DeepSeek v4 Flash?

2

#1 opened 6 months ago by

CCSSNE

New activity in trohrbaugh/Qwen3.6-27B-heretic 6 months ago

Quantized model available?

1

#1 opened 6 months ago by

dieselheart01

New activity in trohrbaugh/Qwen3.6-35B-A3B-heretic 6 months ago

missing tensor

3

#2 opened 6 months ago by

coughmedicine