Skip to content

chore(model-gallery): ⬆️ update checksum #11005

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mudler merged 1 commit into from
Jul 21, 2026
Merged

chore(model-gallery): ⬆️ update checksum #11005

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 2 additions & 16 deletions gallery/index.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,21 +3,7 @@
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/empero-ai/Qwythos-9B-v2-GGUF
description: |
Empero AI

# Qwythos-9B-v2 — the new and improved Qwythos

The next iteration of Qwythos: **all the reasoning of Qwythos-9B, with the looping behavior fixed.** v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use.

- 🔁 **Looping behavior eliminated** — repetition/degeneration under greedy or low-temperature decoding dropped from **6.7% → 0%**. You can serve it *without* leaning on `repetition_penalty` as a band-aid.
- 🧠 **Reasoning fully preserved** — MMLU, GSM8K, GPQA, ARC and HumanEval are all held at (or above) the v1 level. This is a *hygiene* upgrade, not a capability regression.
- 🧩 **MTP head restored** — the native multi-token-prediction module (dropped in the previous export) is back, so config and weights agree and speculative-decoding setups work.
- 🪪 **Cleaner identity** — the model no longer prefaces unrelated answers with its identity; it introduces itself only when you actually ask.
- 🔓 **Still intentionally uncensored** for research, cybersecurity, red-teaming, biology, chemistry, pharmacology and clinical work.
- 📜 **St

...
description: "Empero AI\n\n# Qwythos-9B-v2 — the new and improved Qwythos\n\nThe next iteration of Qwythos: **all the reasoning of Qwythos-9B, with the looping behavior fixed.** v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use.\n\n - \U0001F501 **Looping behavior eliminated** — repetition/degeneration under greedy or low-temperature decoding dropped from **6.7% → 0%**. You can serve it *without* leaning on `repetition_penalty` as a band-aid.\n - \U0001F9E0 **Reasoning fully preserved** — MMLU, GSM8K, GPQA, ARC and HumanEval are all held at (or above) the v1 level. This is a *hygiene* upgrade, not a capability regression.\n - \U0001F9E9 **MTP head restored** — the native multi-token-prediction module (dropped in the previous export) is back, so config and weights agree and speculative-decoding setups work.\n - \U0001FAAA **Cleaner identity** — the model no longer prefaces unrelated answers with its identity; it introduces itself only when you actually ask.\n - \U0001F513 **Still intentionally uncensored** for research, cybersecurity, red-teaming, biology, chemistry, pharmacology and clinical work.\n - \U0001F4DC **St\n\n...\n"
license: "apache-2.0"
tags:
- llm
Expand Down Expand Up @@ -525,7 +511,7 @@
files:
- filename: ds4flash.gguf
uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-GGUF
sha256: 54abd2e5620f88dc59db8fc22967932b0318384bb595464a42569a9e58a06c2d
sha256: 4127d81b1d77a8b71170c8e41186d60abe19e851ebfeabd817d269d3269f9ea7
- name: "qwopus3.6-35b-a3b-coder-mtp"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
Expand Down
Loading