Coenraad

dagelf

·

https://wish.org.za

AI & ML interests

Meta epistemology

Recent Activity

new activity about 1 month ago

huggingface/InferenceSupport:NaiveAI/Naive-N0.5-Flash

new activity about 1 month ago

prism-ml/Ternary-Bonsai-2-27B-gguf:出一个Q6的试试？看看能力能不能保留FP16的99.99%？

new activity about 1 month ago

prism-ml/Ternary-Bonsai-2-27B-gguf:Joining your group

View all activity

Organizations

New activity in huggingface/InferenceSupport about 1 month ago

NaiveAI/Naive-N0.5-Flash

#12668 opened about 1 month ago by

New activity in prism-ml/Ternary-Bonsai-2-27B-gguf about 1 month ago

出一个Q6的试试？看看能力能不能保留FP16的99.99%？

#26 opened about 1 month ago by

Joining your group

#28 opened about 1 month ago by

This model is HORRIBLE for coding. don't waste your time.

#22 opened about 1 month ago by

will this work on AMD card

#13 opened about 1 month ago by

New activity in unsloth/README 8 months ago

https://huggingface.co/YuanLabAI A model to watch

#23 opened 8 months ago by

New activity in openbmb/MiniCPM-o-4_5-gguf 9 months ago

Randomly does reasoning in LMStudio, but reasoning not indicated in model.json

#4 opened 9 months ago by

New activity in openbmb/MiniCPM-V 9 months ago

Random reasoning

#8 opened 9 months ago by

New activity in huggingface/InferenceSupport 10 months ago

manifestai/powercoder-3b

#7041 opened 10 months ago by

Qwen/Qwen3-VL-32B-Thinking-FP8

#7040 opened 10 months ago by

New activity in dphn/dolphin-2.5-mixtral-8x7b over 2 years ago

Adding `safetensors` variant of this model

#23 opened over 2 years ago by

New activity in Efficient-ML/LLaMA-3-8B-SmoothQuant-4bit-4bit over 2 years ago

Why is this exactly the same size as the 8-bit one?

#1 opened over 2 years ago by

New activity in CohereLabs/c4ai-command over 2 years ago

Question

#2 opened over 2 years ago by

New activity in SinclairSchneider/dbrx-instruct-quantization-fixed over 2 years ago

Some error when running

#1 opened over 2 years ago by

New activity in upstage/SOLAR-10.7B-Instruct-v1.0 almost 3 years ago

Does this model support multi-turn conversations?

#18 opened almost 3 years ago by