Timothy Rohrbaugh PRO

trohrbaugh's activity

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

New activity in trohrbaugh/ZAYA1-74B-preview-heretic about 1 month ago

IMO after trying it in VLLM with custom kernels

1

#1 opened about 1 month ago by

coughmedicine

New activity in Zyphra/ZAYA1-74B-preview about 1 month ago

Multi-GPU inference requires 6 patches to modeling_zaya.py

2

#2 opened about 1 month ago by

trohrbaugh

New activity in trohrbaugh/Qwen3.6-27B-heretic-ara about 1 month ago

Bug found

1

#2 opened about 1 month ago by

trohrbaugh

could you make an uncensored version of DeepSeek v4 Flash?

2

#1 opened about 1 month ago by

CCSSNE

New activity in trohrbaugh/Qwen3.6-27B-heretic about 2 months ago

Quantized model available?

1

#1 opened about 2 months ago by

dieselheart01

New activity in trohrbaugh/Qwen3.6-35B-A3B-heretic about 2 months ago

missing tensor

3

#2 opened about 2 months ago by

coughmedicine

New activity in trohrbaugh/gemma-4-31b-it-heretic-ara about 2 months ago

Will you update the chat_template.jinja amd tokenizer_config.json?

1

#4 opened about 2 months ago by

DazzlingShadow

New activity in trohrbaugh/gemma-4-26B-A4B-it-heretic-ara-v2 2 months ago

Whats new with the v2?

1

#1 opened 2 months ago by

Ernigma

New activity in trohrbaugh/gemma-4-31b-it-heretic-ara 2 months ago

french and other unwanted output

16

#2 opened 2 months ago by

sccwq46

New activity in RadicalNotionAI/MiniMax-M2.5-bf16-heretic 2 months ago

How much ram and VRAM did this take?

7

#1 opened 2 months ago by

EclipseMist

New activity in trohrbaugh/gemma-4-31b-it-heretic-ara 2 months ago

Heretic changes

1

#1 opened 2 months ago by

kannalo

New activity in RadicalNotionAI/GLM-4.7-heretic-fp8 2 months ago

New Compression Recipe that follows Zai's own.

#1 opened 2 months ago by

trohrbaugh

New activity in DontPlanToEnd/UGI-Leaderboard 2 months ago

please evaluate trohrbaugh/GLM-4.7-heretic!

👍 1

1

#630 opened 2 months ago by

trohrbaugh

New activity in DontPlanToEnd/UGI-Leaderboard 3 months ago

Please eval! thank you!

#629 opened 3 months ago by

trohrbaugh

New activity in nvidia/Nemotron-Cascade-2-30B-A3B 3 months ago

modeling_nemotron_h.py: Multiple bugs in HybridMambaAttentionDynamicCache break generation with CUDA fast path

2

#13 opened 3 months ago by

trohrbaugh

New activity in DontPlanToEnd/UGI-Leaderboard 3 months ago

Eval requst: Qwen3.5-397B-A17B-heretic

➕ 2

#599 opened 3 months ago by

trohrbaugh

New activity in trohrbaugh/Qwen3.5-122B-A10B-heretic-nvfp4 3 months ago

How are you running this?

11

#1 opened 3 months ago by

infernix

New activity in trohrbaugh/Qwen3.5-122B-A10B-heretic 3 months ago

Template issues: tool calling?

2

#2 opened 3 months ago by

ComputeWisely