Tom Whitworth
twhitworth
AI & ML interests
Low Level Infrastructure, Tooling, Busyforking
Recent Activity
liked a model 8 days ago
Intel/gemma-4-31B-it-int4-AutoRound liked a model 8 days ago
k2-fsa/OmniVoice liked a model 10 days ago
nvidia/nemotron-ocr-v2Organizations
auto round version plz
2
#1 opened 5 months ago
by
twhitworth
Could we get more w2a16 w3a16 and w4a16 Autoround
π 1
1
#1 opened 5 months ago
by
twhitworth
Running on 6 GPUs
π€ 1
4
#10 opened 6 months ago
by
0xSero
v0.0.1
#1 opened 6 months ago
by
twhitworth
Update README.md
#2 opened 6 months ago
by
twhitworth
v0.2.0 Release
#6 opened 7 months ago
by
twhitworth
Happy to announce version v0.2.0 awq-w4a16
3
#5 opened 7 months ago
by
twhitworth
Question about model size
2
#4 opened 7 months ago
by
mhenning
Create README.md
2
#1 opened 8 months ago
by
twhitworth
gptq 8 please champs
1
#2 opened 8 months ago
by
groxaxo
repulled weights but getting this error assert hidden_states.dtype == torch.bfloat16, "hidden_states must be bfloat16"
1
#5 opened 8 months ago
by
bluenevus
getting a couple of errors " No model.safetensors.index.json found in remote" and "assert hidden_states.dtype == torch.bfloat16, "hidden_states must be bfloat16"
π€ 1
1
#1 opened 8 months ago
by
bluenevus
Upload 81 files
#4 opened 8 months ago
by
twhitworth
AWQ 4Bit / GPTQ with full precision gates and head? Please
8
#4 opened 9 months ago
by
chriswritescode
Large audio files
1
#7 opened 9 months ago
by
nherve
Semantic VAD?
1
#5 opened 9 months ago
by
twhitworth
Candle Support
1
#2 opened 9 months ago
by
Idealson
VRAM requirements
π 1
1
#1 opened 10 months ago
by
twhitworth
Out of Mem for 4090-24G
π 1
2
#1 opened 10 months ago
by
GUESSGUO
4a16 quant?
1
#1 opened 11 months ago
by
twhitworth