matatonic
matatonic
AI & ML interests
None yet
Recent Activity
new activity
about 15 hours ago
YiXin-AILab/YiXin-Distill-Qwen-72B:Can you quantify 4.5bpw of this model?
updated
a model
1 day ago
matatonic/OlympicCoder-32B-6.5bpw-h8-exl2
published
a model
1 day ago
matatonic/OlympicCoder-32B-6.5bpw-h8-exl2
Organizations
None yet
matatonic's activity
Can you quantify 4.5bpw of this model?
2
#1 opened about 22 hours ago
by
xldistance
Can you train this model for 4.5bpw quantization?
2
#1 opened 12 days ago
by
xldistance
Can you produce a 4.5bpw quantized model of this model?
2
#1 opened 14 days ago
by
xldistance
Running 1776 with draft model
1
#1 opened 20 days ago
by
ernestr

Rename gptq_model-4bit-128g.safetensors to model.safetensors
#1 opened 3 months ago
by
matatonic
Rename gptq_model-4bit-128g.safetensors to model.safetensors
#7 opened 3 months ago
by
matatonic
Support added to openedai-vision
1
#2 opened 5 months ago
by
matatonic
Updated models no longer require tensorflow
#5 opened 6 months ago
by
matatonic
conversion script please
5
#2 opened 6 months ago
by
ctranslate2-4you
config.json breaking change?
2
#4 opened 6 months ago
by
matatonic
MiniMokney - typo?
1
#1 opened 6 months ago
by
matatonic
float8_e5m2 weights?
1
#4 opened 6 months ago
by
matatonic
xcomposer2d5 3rd party sft support
3
#12 opened 8 months ago
by
tastelikefeet
How to load without lmdeploy?
6
#1 opened 10 months ago
by
matatonic
Higher perplexity than Meta-Llama-3-70B-Instruct? Meta-Llama-3-8B-Instruct-abliterated was lower.
2
#1 opened 10 months ago
by
matatonic
Fix invalid quotes in modeling_360vl.py
5
#1 opened 10 months ago
by
matatonic
multi-gpu support?
4
#9 opened 11 months ago
by
matatonic
FYI: support added to openedai-vision
1
#8 opened 11 months ago
by
matatonic
problem loading tokenizer
5
#4 opened 11 months ago
by
matatonic
OpenAI compatible moderations server
1
#1 opened 12 months ago
by
matatonic