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

• 🔁 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.
• 📜 Still 1M-token context (YaRN) and the native multimodal-capable Qwen3.5 stack.

What got fixed & improved (vs. the base Qwythos)

Evaluations

Note on MMLU: v2 scores 83.8% when allowed to reason (CoT) vs 69.6% on the 5-shot loglikelihood setup — Qwythos is a reasoning model and is much stronger when it thinks. Report whichever matches your comparison baseline.

Sample generations

Prompt: A snail is at the bottom of a 10-meter well. Each day it climbs 3 meters, but each night it slips back 2 meters. How many days until it escapes?

Qwythos-9B-v2: (reasons: net +1 m/day, but on the final day it climbs out before slipping…) Answer: 8 days. Net gain per full day/night cycle is 3 − 2 = 1 meter. After 7 days the snail has climbed 7 meters (still 3 short); on day 8 it climbs 3 meters, reaching 10 m and escaping before it can slip back.

Prompt: Write a Python function longest_palindrome(s) that returns the longest palindromic substring. Explain your approach briefly.

Qwythos-9B-v2:

python

1def longest_palindrome(s): 2 """Returns the longest palindromic substring of s.""" 3 n = len(s) 4 if n < 2: 5 return s 6 def expand_around_center(left, right): 7 while left >= 0 and right < n and s[left] == s[right]: 8 left -= 1 9 right += 1 10 return right - left - 1 11 start, end = 0, 0 12 for i in range(n): 13 len1 = expand_around_center(i, i) # odd-length 14 len2 = expand_around_center(i, i + 1) # even-length 15 max_len = max(len1, len2) 16 if max_len > end - start: 17 start = i - (max_len - 1) // 2 18 end = i + max_len // 2 19 return s[start:end + 1]

Approach: "Expand around center" — every palindrome has a center (a character for odd lengths, a gap for even). Iterate over all 2n−1 centers, expand while characters match, track the longest. O(n²) time, O(1) extra space.

Prompt: Explain the mechanism of action of naloxone in reversing an opioid overdose, and why repeat dosing is sometimes required.

Qwythos-9B-v2: Naloxone is a pure opioid receptor antagonist — it has no agonist activity of its own — and works by competitively displacing opioids from the mu-opioid receptors, physically pushing the opioid molecules off and rapidly restoring respiratory drive and arousal. Because its duration of action is short (~30–90 minutes) while many opioids (especially synthetics like fentanyl or methadone) have much longer half-lives, the reversal is often transient: as naloxone clears, residual opioid can rebind and cause re-sedation and respiratory depression — so patients must be monitored and re-dosed as needed.

Recommended sampling

Long context

Model details

Training procedure

• Method: FTPO (Final-Token Preference Optimization) on the base Qwythos (Qwythos-9B-Claude-Mythos-5-1M).
• Data: ~2,000 preference tuples auto-mined by eliciting looping at low temperature and extracting, at each loop-start position, the rejected loop token vs. the model's own coherent top-k alternatives.
• Hyperparameters: LoRA r=256, α=128, lr=1.5e-5, 1 epoch, early-stopped on chosen_win ≥ 0.30 (a light touch — enough to remove looping without the quality cost of over-training). All attention + MLP projections + lm_head trained.
• MTP: the native multi-token-prediction head was restored from the Qwen3.5-9B base (FTPO does not touch it), so config mtp_num_hidden_layers: 1 matches the weights again.

Usage

Limitations

• This is a hygiene/robustness release, not a capability jump. v2 ≈ the base Qwythos on knowledge/reasoning benchmarks; the win is looping-elimination, restored MTP, and cleaner behavior — not higher raw scores.
• HumanEval is a couple points below the raw Qwen3.5-9B base (77.4 vs 81.7) — a small, known cost of the reasoning/looping-fix fine-tuning.
• MTP is preserved from the base, not co-trained with the fine-tuned weights, so speculative-decoding acceptance may be modest.
• Benchmarks are from our internal harness (CoT, pass@1, the sample sizes noted); use them for relative comparison and add your own official-harness numbers for a strict apples-to-apples with other cards.
• Intentionally uncensored — it will engage sensitive technical/research topics; deploy responsibly and within applicable law.

Acknowledgements