HCHs/RivetCoder-9B-A4B
Text Generation • 9B • Updated • 5
🦀 dancing crab
Damien
el4
AI & ML interests
I do anything really | #quantwizard | ETH: 0xDEE7fa8C421BD038D32e4441ea1aDe72fE973706
Recent Activity
new activity about 6 hours ago
el4/Qwen3.8-27B-ONYX-GGUF:YES!!! Thrilled to see; will test mini vs. UD-IQ3_XXS liked a model about 19 hours ago
HCHs/RivetCoder-9B-A4B liked a model 1 day ago
RedHatAI/GLM-5.3-Flash-NVFP4Organizations
None yet
YES!!! Thrilled to see; will test mini vs. UD-IQ3_XXS
🔥 3
5
#2 opened 12 days ago
by 
NeatOnTheRocks
liked a
model about 19 hours ago
liked a
model 1 day ago
liked a
model 3 days ago
my guess is its a low param version of GLM
thinking traces are glm like and it struggled writing awesomewm lua- glm 5.2 handles awesomewm lua flawlessly
so my money is on low parameter glm
liked a
model 6 days ago
WOAH- this quant work is amazing! 🔥
#1 opened 7 days ago
by el4
liked 2
models 7 days ago
Request: DOI
🔥 1
1
#139 opened 11 days ago
by 
Bimzypermanent
reacted to SeaWolf-AI's post with ❤️ 12 days ago
Post
4288
🧬 Your AI can design a malaria drug candidate. Can it tell you whether it's any good?
Open Discovery Challenge #1 — Malaria is live. Design a molecule with any model — OpenAI, Claude, Gemini, Qwen, KIMI, DeepSeek, open weights, or by hand — submit it as SMILES, and it's scored in minutes on whole-cell activity, target binding, selectivity over the human enzyme, ADMET, novelty and synthesisability.
You can check the scoring instead of trusting it. Approved drugs sit on the same leaderboard as the entries: DSM265, a clinical-stage antimalarial, scores 50.9. Teriflunomide — approved, but it hits the human enzyme — scores 2.8. Caffeine scores 1.8. If the clinical candidate lands on top and coffee lands at the bottom, the scorer discriminates.
We caught 14 defects before opening — conventional toxicity cutoffs rejected all three approved antimalarials and coffee. All written up, along with the rule we now hold everything to: a gate that rejects an approved drug is a broken gate.
Your molecule stays yours. No patent interest, nothing into our pipeline. You choose whether it's published — and publishing can cost you patentability, so we say so.
USD 1,000 to the top entry when Season #1 closes 30 September 2026 — not payment for your tokens, but a way of saying the work had worth.
Malaria killed ~597,000 people in 2023, three quarters of them children under five. Not for want of chemistry — for want of a market.
No chemistry needed: the guide ships five prompts you can paste straight into your model, and the full rubric is published.
📖 https://huggingface.co/blog/FINAL-Bench/open-discovery-challenge
🚀 FINAL-Bench/open-discovery-challenge
Computational assessments of candidates — not measurements, not claims of efficacy.
Open Discovery Challenge #1 — Malaria is live. Design a molecule with any model — OpenAI, Claude, Gemini, Qwen, KIMI, DeepSeek, open weights, or by hand — submit it as SMILES, and it's scored in minutes on whole-cell activity, target binding, selectivity over the human enzyme, ADMET, novelty and synthesisability.
You can check the scoring instead of trusting it. Approved drugs sit on the same leaderboard as the entries: DSM265, a clinical-stage antimalarial, scores 50.9. Teriflunomide — approved, but it hits the human enzyme — scores 2.8. Caffeine scores 1.8. If the clinical candidate lands on top and coffee lands at the bottom, the scorer discriminates.
We caught 14 defects before opening — conventional toxicity cutoffs rejected all three approved antimalarials and coffee. All written up, along with the rule we now hold everything to: a gate that rejects an approved drug is a broken gate.
Your molecule stays yours. No patent interest, nothing into our pipeline. You choose whether it's published — and publishing can cost you patentability, so we say so.
USD 1,000 to the top entry when Season #1 closes 30 September 2026 — not payment for your tokens, but a way of saying the work had worth.
Malaria killed ~597,000 people in 2023, three quarters of them children under five. Not for want of chemistry — for want of a market.
No chemistry needed: the guide ships five prompts you can paste straight into your model, and the full rubric is published.
📖 https://huggingface.co/blog/FINAL-Bench/open-discovery-challenge
🚀 FINAL-Bench/open-discovery-challenge
Computational assessments of candidates — not measurements, not claims of efficacy.
- 12 replies
Just Curious...
3
#1 opened 13 days ago
by 
Czavodsky
Q4_K_M gets wrong output using kobold.cpp
6
#55 opened 13 days ago
by 
Blizado
Amazing model
🔥 2
42
#2 opened 21 days ago
by 
ahmedsevenup
updated a
model 13 days ago
updated a
collection 13 days ago
liked a
model 13 days ago
published a
model 13 days ago
liked a
model 13 days ago
liked a
model 15 days ago
