YuJuLin
nps798
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-4bit:Does it work with oMLX? new activity 10 days ago
prism-ml/Ternary-Bonsai-27B-mlx-2bit:Ternary-Bonsai-27B-mlx-2bit slow on macbook 4 pro with oMLXOrganizations
None yet
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 3 days ago
VERSION: MLX --- Can we also get oMLX version? with MTP support plz
❤️👍 1
2
#37 opened 3 days ago
by nps798
Does it work with oMLX?
1
#1 opened 3 days ago
by nps798
Ternary-Bonsai-27B-mlx-2bit slow on macbook 4 pro with oMLX
2
#2 opened 10 days ago
by nps798
is it available to change output text format to Markdown?
10
#21 opened almost 2 years ago
by 
MhmdSyd
Why do you add a normalize layer in the end of the model? Does it affect how we fine tune results?
3
#13 opened over 2 years ago
by nps798
How do you build your own MoE model?
4
#1 opened over 2 years ago
by nps798
The same audio. Why are the results on Hugging Face different from the results of the model on GitHub?
1
#31 opened over 2 years ago
by 
deepsadness
厲害！請教預訓練所需硬體資源 以及訓練代碼原理
3
#2 opened over 2 years ago
by nps798
Has a massive repetition problem
14
#29 opened almost 3 years ago
by 
Delcos
finetuning
3
#1 opened almost 3 years ago
by 
almugabo
Hi what did you train this model with, and what were hyperparams?
7
#1 opened almost 3 years ago
by 
teknium
How is this model different from Llama 2-7B?
7
#8 opened almost 3 years ago
by 
dheerajpai
using oobaboga to load model fail for 70b chat ggml Q2_k anad Q3_K_S
2
#2 opened about 3 years ago
by nps798