cd /news/machine-learning/seeking-feedback-on-token-block-cont… · home topics machine-learning article
[ARTICLE · art-99497] src=discuss.huggingface.co ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Seeking feedback on token-block context selection for long-sequence QLoRA fine-tuning

An experimental training-time context-selection prototype, SpiralCoreAttention, achieved a mean training-step speedup of 1.675× and reduced peak VRAM by 6.036 GB during QLoRA fine-tuning of Qwen2.5-7B-Instruct on 8,192-token sequences using one RTX PRO 6000 Blackwell GPU, with no worsening of held-out full-context loss in short runs. The developer, cannural2-cpu, released the code and methodology on GitHub and is seeking technical feedback on the evaluation protocol, task-level quality evaluations, baselines, and failure modes.

read1 min views1 publishedAug 17, 2026

Hi everyone,

I’m building SpiralCoreAttention, an experimental training-time context-selection prototype for open-weight LLM fine-tuning.

Instead of passing the complete long sequence through every training forward/backward pass, the prototype selects token blocks from the sequence, trains on that selected context, and evaluates the resulting adapter on held-out full-context sequences.

I recently ran an internal QLoRA experiment with:

Qwen2.5-7B-Instruct 4-bit NF4 QLoRA

one RTX PRO 6000 Blackwell GPU

8,192-token sequences

48 training steps per run

three seeds

60% selected-context configuration

Across the three internal runs, mean training-step speedup was 1.675× and peak VRAM was 6.036 GB lower. Held-out full-context loss did not worsen in these short runs.

Important limitations: this is a local-corpus, short-duration, single-GPU research result. It is not a production claim, a task-level quality proof, distributed-training result, or evidence for full pretraining / 70B-scale training.

Code, methodology, exact seed-level results, and limitations:

https://github.com/cannural2-cpu/SpiralCoreAttention I would appreciate technical feedback on:

Whether this is a reasonable evaluation protocol for selected-context fine-tuning

Which task-level quality evaluations I should add next

Whether there are established baselines or papers I should compare against

Failure modes I should test before attempting a real design-partner validation

Thank you.

── more in #machine-learning 4 stories · sorted by recency
── more on @spiralcoreattention 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/seeking-feedback-on-…] indexed:0 read:1min 2026-08-17 ·