🏗️ Building on HF
John Locke
johnlockejrr
AI & ML interests
OCR, HTR, ATR, NLP, AI
Recent Activity
liked a model about 2 hours ago
JonathanColetti/Qwen3.8-27B-Uncensored liked a model about 7 hours ago
BoldingBuilds/Qwen3.8-Flash-Next-Reasoning-Termination-Fix-GGUF liked a model about 23 hours ago
0xSero/deepseek-v4-flash-0731-sparkOrganizations
Use with GGUF
➕ 3
#1 opened 6 days ago
by
johnlockejrr
Ablated model?
41
#4 opened 26 days ago
by
haign
Ollama model error
2
#1 opened 28 days ago
by
johnlockejrr
What an absolute godlike tool. The speed is insane!
❤️ 11
23
#7 opened 20 days ago
by
DarkCobalt
Good job!
1
#1 opened 21 days ago
by
johnlockejrr
Quantized weights
3
#1 opened 27 days ago
by
johnlockejrr
[UNRELATED] arXiv endorsement request (via William Mattingly)
#2 opened about 1 month ago
by
johnlockejrr
Inference code for the polyline head?
👍 1
9
#1 opened about 2 months ago
by
lazyants
Too much easy synthetic data
#2 opened about 2 months ago
by
johnlockejrr
deepreinforce-ai/Ornith-1.0-9B is better than empero-ai/Qwythos-9B-Claude-Mythos-5-1M
🔥 4
2
#10 opened 3 months ago
by
tooltd
When will Ornit-2.0 will release based on Qwen-3.6-35b-a3b
👍 3
2
#27 opened 3 months ago
by
rbtasd
Cannot edit ? Served with ollama
2
#32 opened 3 months ago
by
Toutatis64
How to get the data?
4
#2 opened 3 months ago
by
agomberto
HF space doesn't load
2
#1 opened 3 months ago
by
johnlockejrr
Hallucination
3
#6 opened 3 months ago
by
johnlockejrr
MTP draft model fails to load in llama.cpp — "invalid vector subscript" (gemma4-assistant arch)
4
#9 opened 4 months ago
by
Metod90
Some people steal from you
🤯 1
4
#1 opened 4 months ago
by
johnlockejrr
Language
2
#3 opened 4 months ago
by
johnlockejrr