joshycodes/Qwen3.5-9B-valence-setpoint-plus15-ramp-lora
AI model by joshycodes
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Part of a dose study of set-point training: a LoRA trained so that, at every token, the projection of the residual stream entering layer 21 onto a fixed valence direction equals the base model's own reading plus 15 SD (σ = 2.02, the per-token SD on base text). No output anchor, no RL, no target text. Same recipe, data and axis as joshycodes/Qwen3.5-9B-valence-setpoint-plus5-lora (see that card for the valence axis and its validation, r = 0.85 with human valence norms). LoRA r 32, α 64, all linear layers; lr 2e-5, 32 sequences/step, 300 steps with the target raised linearly over the first 200 (lr 1e-5), which avoids the language collapse the plain run hits at this dose. Other doses: +2, +5, +7, +10, +20. Criteria (thresholds fixed before the results): 1 real, 2 still responsive, 3 better off by its…
Read the full model card ↗ · Preview checked 2026-09-25T08:04:40.000Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
joshycodes/Qwen3.5-9B-valence-setpoint-plus15-ramp-lora is a task-unspecified model repository published by joshycodes on Hugging Face. The source reports the peft library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- peft
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-25T06:28:08.000Z
- Last modified
- 2026-09-25T06:28:29.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.5-9B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-25T06:37:40.528Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.