violetxi/qwen35-9b-harvey-v4-notes-conditioned-100m-kl-0p05
image-text-to-text model by violetxi
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.
Full Qwen3.5-9B model trained on 100M notes + note-conditioned trajectory tokens, with KL coefficient 0.05. This revision is checkpoint-3068, after 2 epoch(s) and 3,068 updates. The dataset contains 99,998,917 supervised tokens per epoch before causal shifting: 69,999,985 note tokens and 29,998,932 assistant trajectory tokens. After shifting, each epoch has 99,993,091 supervised tokens. The full run trains for two epochs; KL replay is additional. Objective: notes next-token prediction + assistant-masked note-conditioned trajectory next-token prediction + 0.05 × KL(base || student). The frozen reference is Qwen/Qwen3.5-9B at c202236235762e1c871ad0ccb60c8ee5ba337b9a. Replay comes from harvey-kl-ground-sessions: 2,048 sessions, context limit 8,192, up to 128 assistant prediction positions per draw. KL uses the full vocabulary and the mean of session means. Training uses context rows of 16,384 tokens, global batch 8, gradient accumulation 1, learning rate…
Read the full model card ↗ · Preview checked 2026-09-23T09:21:24.428Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
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
violetxi/qwen35-9b-harvey-v4-notes-conditioned-100m-kl-0p05 is a image-text-to-text model repository published by violetxi on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 9,653,104,368
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-23T06:11:13.000Z
- Last modified
- 2026-09-23T06:14:07.000Z
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 2026-09-23T06:37:25.545Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.