Rodri Mora
bullerwins
AI & ML interests
Gen AI, MLOps, Fine tuning and Quantizing models
Recent Activity
new activity
21 days ago
neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic:Calibration dataset
new activity
22 days ago
bullerwins/DeepSeek-V3-GGUF:Add pipeline tag and library name
updated
a model
23 days ago
bullerwins/Qwen2.5-7B-Instruct-GGUF
Organizations
bullerwins's activity
Calibration dataset
1
#1 opened 21 days ago
by
bullerwins

Add pipeline tag and library name
1
#9 opened 22 days ago
by
nielsr

quantization request
4
#1 opened 2 months ago
by
KT313

Please quantize base model too
6
#3 opened 2 months ago
by
Delta36652
Q4 potentially broken
3
#2 opened 2 months ago
by
terribleplan
Update README.md
1
#1 opened 2 months ago
by
bullerwins

minimum vram?
11
#9 opened 3 months ago
by
CHNtentes
It is needed to use bnb 4bit?
1
#3 opened 9 months ago
by
bullerwins

one part
1
#1 opened 6 months ago
by
goodasdgood
Thanks for the Update
1
#1 opened 6 months ago
by
PrimeD
Update config.json
16
#6 opened 6 months ago
by
bullerwins

The tokenizer has changed just fyi
12
#2 opened 8 months ago
by
bullerwins

Proper exllamav2 github branch
2
#1 opened 7 months ago
by
clearcash

8 bit version
3
#3 opened 8 months ago
by
bullerwins

Wrong number of tensors when loading the model.
3
#3 opened 7 months ago
by
CharlaDev
No "No Virus" label
1
#2 opened 7 months ago
by
frbackup
Examples dataset used for GPTQ Calibration
1
#4 opened 8 months ago
by
bullerwins

8 bit version
#3 opened 8 months ago
by
bullerwins

Why is this model crashing my game?
1
#1 opened 8 months ago
by
Keionsa

How to use INT4 with vLLM?
5
#8 opened 8 months ago
by
hfmon