WW2Bench Leaderboard
🏛
1
WW2Bench scores for small language models, v0.1.0.
Wayne Workman PRO
wayneworkman2012
AI & ML interests
LLMs
Recent Activity
published a Space 5 days ago
wayneworkman2012/ww2bench-leaderboard updated a Space 6 days ago
wayneworkman2012/ww2bench-leaderboard updated a Space 8 days ago
wayneworkman2012/peacebell-v1-291M-demo-cpuOrganizations
published a
Space 5 days ago
updated a
Space 6 days ago
updated 2
Spaces 8 days ago
published a
Space 8 days ago
updated a
Space 8 days ago
Encouraging entry into CodeSoft's SLM Arena
😔 1
2
#161 opened 9 days ago
by wayneworkman2012
updated a
Space 8 days ago
updated a
model 8 days ago
an idea - vote on past inputs and outputs
#16 opened 8 days ago
by wayneworkman2012
Open the user inputs
➕ 1
8
#9 opened 27 days ago
by wayneworkman2012
Great job
🤗 1
#1 opened 9 days ago
by wayneworkman2012
liked a
Space 9 days ago
I see you mentioned in the README using gpt and claude. Have you determined this is ok under anthropic's terms? I suppose it is because Anthropic offers no model training framework and therefore it's not competing ?? Not sure on this.
reacted to medmekk's post with ❤️ 9 days ago
Post
4334
🚀 Introducing Halo 1.0
Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle.
It comes with:
🧠 Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
🤖 Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
⚡ ~2.8× TRL throughput on 8× B300 (EP+FSDPv2, FA4, fp8/fp4)
🤗 Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4…)
🛠️ One halo command, prebuilt Docker images, and docs for humans and agents
💻 https://github.com/whitecircle/halo
Try it and tell us what you're training
Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle.
It comes with:
🧠 Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
🤖 Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
⚡ ~2.8× TRL throughput on 8× B300 (EP+FSDPv2, FA4, fp8/fp4)
🤗 Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4…)
🛠️ One halo command, prebuilt Docker images, and docs for humans and agents
💻 https://github.com/whitecircle/halo
Try it and tell us what you're training
- 1 reply
reacted to prithivMLmods's post with 👍 9 days ago
Post
815
VisionGuardrail EVO-2, a multimodal image-classification content-safety model based on Qwen/Qwen3.8-27B, is now available on the Hub!
Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.
➠ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF
➠ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2
➠ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection
⤷ To learn more, visit the app page or the respective model pages.
Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.
➠ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF
➠ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2
➠ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection
⤷ To learn more, visit the app page or the respective model pages.
I read the chat - this is really entertaining. I need to check this out.
liked a
Space 9 days ago
CodeSoft SLM Arena
#9 opened 9 days ago
by wayneworkman2012
reacted to Datdanboi25's post with ❤️ 11 days ago
Post
3459
THE SLM FRONTIER ADVANCES!
bench-labs/cagliostro-v3 just hit an Intelligence Index of 26.13 on the AxiomicLabs/Open_SLM_Leaderboard a 146M-param model trained completely from scratch on a single consumer GPU. That's 2nd place overall, and as far as I can tell, the most capable SLM trained on consumer hardware to date. Beating SmolLM-135m on 1/8th of the data is just silly levels of efficiency.
Big congrats to the @BenchLabs team and specifically @TobiasLogic !
bench-labs/cagliostro-v3 just hit an Intelligence Index of 26.13 on the AxiomicLabs/Open_SLM_Leaderboard a 146M-param model trained completely from scratch on a single consumer GPU. That's 2nd place overall, and as far as I can tell, the most capable SLM trained on consumer hardware to date. Beating SmolLM-135m on 1/8th of the data is just silly levels of efficiency.
Big congrats to the @BenchLabs team and specifically @TobiasLogic !
- 6 replies