Useruser2statsaltalt/MathSupra
Text Generation • 51.8M • Updated • 23 • 1
Jack Voide
Mindweller
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
Useruser2statsaltalt/MathSupra liked a model 1 day ago
PrunaAI/WeiboAI-VibeThinker-3B-HQQ-4bit-smashed liked a model 8 days ago
WeiboAI/VibeThinker-3BOrganizations
liked 2
models 1 day ago
liked a
model 8 days ago
liked a
model 14 days ago
liked a
model 18 days ago
liked a
model 28 days ago
liked a
model 29 days ago
upvoted a paper about 1 month ago
liked a
model about 1 month ago
reacted to qgallouedec's post with 👍 about 1 month ago
Post
10415
Shipped hf-sandbox! 🥡
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
- 1 reply
liked a
model about 2 months ago
reacted to DedeProGames's post with 👍 about 2 months ago
Post
8589
GRaPE 2 Pro is now available.
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
minimal, all the way up to xtra-Hi for deep, extended thought on hard problems. For most agentic use, auto or low is the move to keep things snappy.It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
contact@skinnertopia.com 
- 1 reply
reacted to DavidAU's post with 👍 about 2 months ago
Post
22521
Uncensored, Heretic, Qwen 3.6 27B GGUFs - Exceeds all quant metrics and core model metrics too.
Tuned 27B Heretic Uncensored quants from IQ2M to Q8.
IQ2M is 83% of BF16, with Q6 just under 98% of BF16 precision.
Q8: 98.47% of BF16 precision.
NEO/Code DI-Imatrix Quants.
Exceeds all 5 metrics for "censored" quants too.
All metrics posted.
Tuned model -from which the quants were built- also exceeds Qwen 3.6 27B core metrics too.
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF
Tuned 27B Heretic Uncensored quants from IQ2M to Q8.
IQ2M is 83% of BF16, with Q6 just under 98% of BF16 precision.
Q8: 98.47% of BF16 precision.
NEO/Code DI-Imatrix Quants.
Exceeds all 5 metrics for "censored" quants too.
All metrics posted.
Tuned model -from which the quants were built- also exceeds Qwen 3.6 27B core metrics too.
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF
- 9 replies
reacted to ManniX-ITA's post with 👍 about 2 months ago
Post
3021
🚀 Two releases this week pushing merge methodology forward.
▶ Qwen3.6-27B-Omnimerge-v4-MLP
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4
Same-base DARE-TIES merge of Qwen3.6-27B + 3 fine-tunes (rico03 Claude distill, Esper3.1, kai-os Opus reasoning anchor) via my Omnimerge_v2 method (OBIM-lite + DAREx-q + EMR election).
Hit a Qwen3.6-specific fragility: hyperparams that work flawlessly on 3.5 produced 80% unclosed-<think> on 3.6, collapsing pass@1 to ~20%. Per-tensor delta forensics localized the failure to mlp.{gate,up,down}_proj in
layers 27–52. Fix: MLP-passthrough surgery — copy MLPs verbatim from base, keep merged attn + linear_attn. Leak → 0%.
Q6_K results (vs Qwen3.6 base / vs Omnimerge-v2 on Qwen3.5):
• HumanEval: 84.76% (= base, +5.49 pp vs v2)
• MBPP corrected: 73.40% (+15.80 pp vs base, ≈ v2)
• GPQA Diamond: ~84.75% partial 192/198 (+15.5 pp vs v2)
▶ Qwen3.5-4B Importance-Signal Study (M1..M5)
Controlled 5-way comparison: same Qwen3.5-4B base, same 2 fine-tunes (Jackrong Claude-4.5 distill + Crow Opus-4.6 distill), only the importance signal driving DARE-TIES sparsification varies.
Q6_K HE / MBPP pass@1:
• M1 Vanilla DARE-TIES → 51.22 / 47.00
• M2 OMv2 (no signal) → 52.44 / 49.40
• M3 OMv2 + Fisher → 57.93 🥇 / 48.80
• M4 mergekit ex-LRP (PR #682) → 51.22 / 49.40
• M5 OMv2 + LRP → 53.05 / 51.40 🥇
Findings: Fisher wins HE (+4.88 pp over vanilla), LRP wins MBPP (+2.60 pp). Both signals + Omnimerge_v2 recipe beat vanilla. To make multimodal-LM ex-LRP work end-to-end against Qwen3_5ForConditionalGeneration, I filed
5 patches against arcee-ai/mergekit PR #682 + 1 against rachtibat/lxt.
All five Mx checkpoints + Fisher/LRP signal safetensors + reproducer scripts published.
▶ Qwen3.6-27B-Omnimerge-v4-MLP
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4
Same-base DARE-TIES merge of Qwen3.6-27B + 3 fine-tunes (rico03 Claude distill, Esper3.1, kai-os Opus reasoning anchor) via my Omnimerge_v2 method (OBIM-lite + DAREx-q + EMR election).
Hit a Qwen3.6-specific fragility: hyperparams that work flawlessly on 3.5 produced 80% unclosed-<think> on 3.6, collapsing pass@1 to ~20%. Per-tensor delta forensics localized the failure to mlp.{gate,up,down}_proj in
layers 27–52. Fix: MLP-passthrough surgery — copy MLPs verbatim from base, keep merged attn + linear_attn. Leak → 0%.
Q6_K results (vs Qwen3.6 base / vs Omnimerge-v2 on Qwen3.5):
• HumanEval: 84.76% (= base, +5.49 pp vs v2)
• MBPP corrected: 73.40% (+15.80 pp vs base, ≈ v2)
• GPQA Diamond: ~84.75% partial 192/198 (+15.5 pp vs v2)
▶ Qwen3.5-4B Importance-Signal Study (M1..M5)
Controlled 5-way comparison: same Qwen3.5-4B base, same 2 fine-tunes (Jackrong Claude-4.5 distill + Crow Opus-4.6 distill), only the importance signal driving DARE-TIES sparsification varies.
Q6_K HE / MBPP pass@1:
• M1 Vanilla DARE-TIES → 51.22 / 47.00
• M2 OMv2 (no signal) → 52.44 / 49.40
• M3 OMv2 + Fisher → 57.93 🥇 / 48.80
• M4 mergekit ex-LRP (PR #682) → 51.22 / 49.40
• M5 OMv2 + LRP → 53.05 / 51.40 🥇
Findings: Fisher wins HE (+4.88 pp over vanilla), LRP wins MBPP (+2.60 pp). Both signals + Omnimerge_v2 recipe beat vanilla. To make multimodal-LM ex-LRP work end-to-end against Qwen3_5ForConditionalGeneration, I filed
5 patches against arcee-ai/mergekit PR #682 + 1 against rachtibat/lxt.
All five Mx checkpoints + Fisher/LRP signal safetensors + reproducer scripts published.
- 1 reply
liked a
model about 2 months ago
liked a
Space about 2 months ago
liked 3
models about 2 months ago
liked a
model 2 months ago
