Jari Katajisto
kataguru
AI & ML interests
Sovereign High-Performance Finnish LLMs. Developing uncensored, deeply Finnish-reasoning language models for local inference (vLLM / AWQ & GGUF). Focus: Linguistic sovereignty, epistemic honesty, and autonomous SWE agents.
Recent Activity
updated a model 5 days ago
kataguru/Industry-Coder-27B-v2.0 published a model 5 days ago
kataguru/Industry-Coder-27B-v2.0 updated a model 5 days ago
kataguru/Industry-Coder-27B-v2.0-GGUFOrganizations
None yet
Error load from LM Studio 0.4.25
1
#1 opened about 1 month ago
by 
Abramoff
Fix architecture name in config.json ("Qwen3_5_MoeForConditionalGeneration" -> "Qwen3_5MoeForConditionalGeneration")
1
#1 opened about 2 months ago
by kataguru
New activity in DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored about 2 months ago
Bug: chat_template pre-scan raises 'System message cannot contain images.' for user messages with images
👀 1
1
#13 opened about 2 months ago
by kataguru
New activity in TheUnderscore/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-W4A16-AWQ about 2 months ago
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 4 months ago
finetune Qwen3.5-122B-A10B on this corpus?
🤗👍 4
2
#16 opened 4 months ago
by 
ashbash