Djuunaa
djuna
·
AI & ML interests
None yet
Recent Activity
liked a model about 21 hours ago
ScienceOne-AI/S1-VL-32B-RL new activity about 21 hours ago
zerofata/Q3.5-BlueStar-v2-27B:q3.6? reacted to imnotkitty's post with 🔥 about 21 hours ago
https://huggingface.co/spaces/tencent/Hy3-preview is out: an open-weights MoE reasoning model.
✅ 295B total / 21B active / 256K context
✅ Fused fast-and-slow thinking in a single model
✅ First model trained on Hunyuan's rebuilt pretraining + RL infra (Feb → Apr)
Benchmarks:
👉 SWE-Bench Verified, Terminal-Bench 2.0, BrowseComp, WideSearch — competitive results, particularly strong on agentic tool use
👉 Top score on Tsinghua's 2026 Spring math PhD qualifying exam
👉 Strong context-learning and instruction-following on Tencent's CL-bench / CL-bench-Life
More details can be found in my article: https://huggingface.co/blog/imnotkitty/hy3-previewOrganizations
spaces 6
Paused
Agents
18
mergekit-gui
🔀
Merge and upload models using a YAML config
Running
Gradient Array Slider
🐢
Gradient Array Slider (for mergekit)
Paused
Agents
1
Replete Qwen2 1.5B Instruct
💬
Running
Llama Pro Dry Run
⚡
Calculate duplicated layers for model expansion
Running
3
Chat Template Tester
🌍
Experiment with Chat Template
Running
5
Generate Mergkit For Upscale LLM
📈
Generate YAML config for model slicing
models 100
djuna/Q3-IIJAN-3B-Q8_0-GGUF
4B • Updated • 5
djuna/DeepSeek-R1-0528-Qwen3-8B-remap
Text Generation • 8B • Updated • 6
djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap
Text Generation • 15B • Updated • 11 • 2
djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-remap
Text Generation • 15B • Updated • 4 • 1
djuna/MN-Chinofun-12B-4-4bit
Text Generation • 2B • Updated • 15
djuna/TEST3-Q2.5-Lenned-14B-Q5_K_M-GGUF
15B • Updated • 4
djuna/TEST3-Q2.5-Lenned-14B
Text Generation • 15B • Updated • 6 • 1
djuna/TEST2-Q2.5-Lenned-14B-Q5_K_M-GGUF
15B • Updated • 2 • 1
djuna/TEST2-Q2.5-Lenned-14B
Text Generation • 15B • Updated • 4 • 4
djuna/TEST-Q2.5-Lenned-14B
Text Generation • 15B • Updated • 6 • 1
datasets 0
None public yet