name's picture

22 1

name

abiteddie

·

andreas.pracht@gmx.de

AI & ML interests

None yet

Recent Activity

new activity 6 days ago

AliceThirty/Step-3.5-Flash-gguf:Not working

new activity 4 months ago

QuantTrio/Qwen3-VL-30B-A3B-Thinking-AWQ:128GB Error

new activity 5 months ago

ByteDance-Seed/Seed-OSS-36B-Instruct:super bad german

View all activity

Organizations

None yet

New activity in AliceThirty/Step-3.5-Flash-gguf 6 days ago

Not working

#1 opened 6 days ago by

New activity in QuantTrio/Qwen3-VL-30B-A3B-Thinking-AWQ 4 months ago

128GB Error

#1 opened 4 months ago by

New activity in ByteDance-Seed/Seed-OSS-36B-Instruct 5 months ago

super bad german

#28 opened 5 months ago by

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 5 months ago

GGUF when? 8 bit quant when?

#1 opened 5 months ago by

New activity in Qwen/Qwen3-Next-80B-A3B-Thinking 5 months ago

Good for Roleplay - Sucks at tool calling

#13 opened 5 months ago by

New activity in OpenGVLab/InternVL3_5-38B 5 months ago

vLLM compatiblility

#2 opened 6 months ago by

New activity in QuantTrio/GLM-4.5V-AWQ 6 months ago

Not running ond vllm / transformer

#3 opened 6 months ago by

New activity in QuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ 6 months ago

Quant Error

#2 opened 6 months ago by

New activity in OpenGVLab/InternVL3-78B-AWQ 6 months ago

Tensor parallel size

#1 opened 10 months ago by

New activity in TheDrummer/Valkyrie-49B-v1 8 months ago

Any chance for awq or gptq ?

#3 opened 8 months ago by

New activity in mlabonne/gemma-3-27b-it-abliterated 8 months ago

awq version?

#10 opened 8 months ago by

New activity in ByteDance-Seed/UI-TARS-1.5-7B 8 months ago

Error bbox locating

#3 opened 10 months ago by

upvoted a collection 9 months ago

Current Series

Intelligent LLMs with a knack for storytelling and RP / ERP. • 13 items • Updated Jul 1, 2025 • 12

New activity in huihui-ai/Qwen3-14B-abliterated 9 months ago

Can you train the abliterated model of qwen3-32b?

#2 opened 9 months ago by

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1 10 months ago

Seeking Advice on Fine-Tuning for Domain Reasoning Tasks

#4 opened 11 months ago by

commented a paper 10 months ago

LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models

Paper • 2405.18377 • Published May 28, 2024 • 21 •

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1 10 months ago

TypeError: DeciLMPreTrainedModel._prepare_generation_config() takes 2 positional arguments but 3 were given

#11 opened 10 months ago by

New activity in DavidAU/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-gguf 11 months ago

Yup, LM Studio won't work without changing the model setting.

#1 opened 11 months ago by

New activity in Steelskull/L3.3-Damascus-R1 about 1 year ago

No reasoning

#1 opened about 1 year ago by

New activity in DavidAU/DeepSeek-V2-Grand-Horror-SMB-R1-Distill-Llama-3.1-Uncensored-16.5B-GGUF about 1 year ago

No Output on lm studio

#1 opened about 1 year ago by