Nikolay Kozlov
NikolayKozloff
AI & ML interests
None yet
Recent Activity
liked
a model
about 2 hours ago
kyutai/hibiki-2b-pytorch-bf16
liked
a model
about 6 hours ago
tinybiggames/DeepSeek-R1-Distill-Llama-8B-abliterated-Q4_K_M-GGUF
liked
a Space
about 8 hours ago
fffiloni/YuE
Organizations
NikolayKozloff's activity
Thanks for great model. I tried to create q8 gguf using HF gguf-my-repo but got this error:
#2 opened 4 months ago
by
NikolayKozloff
Update converting script, please. Llama.cpp added support for Falcon Mamba architecture.
#114 opened 6 months ago
by
NikolayKozloff
Please, update converting script. Llama.cpp added support for Nemotron and Minitron architectures.
3
#111 opened 6 months ago
by
NikolayKozloff
Hello. Thank you for this nice adapter. Could you upload the full model, please?
3
#1 opened 10 months ago
by
NikolayKozloff
Could you create a GGUF-version of this base-model?
4
#1 opened 8 months ago
by
AiCreatornator
Upgrade Gradio to avoid white screen issues
3
#5 opened 8 months ago
by
cbensimon
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1617550879179-noauth.jpeg)
Custom tokenizer support for llama.cpp?
9
#2 opened 9 months ago
by
akx
Upload model.safetensors
3
#2 opened 8 months ago
by
klei09
Error quantizing: b'/bin/sh: 1: ./llama.cpp/quantize: not found\n'
9
#87 opened 8 months ago
by
NikolayKozloff