Jeesup/llama3_8b_instruct_remove_40_seed42_jbbbenresp13_calib
AI model by Jeesup
Older snapshot: check the original source for current information.
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.
/home/jeesup0103/svdsafety/assets/models/Llama-3-8B-Instruct compressed with the complete SVD-LLM method (AIoT-MLSys-Lab/SVD-LLM, commit 7538cca98880), run as the authors' code rather than reimplemented. Llama-2 is multi-head, so component/svdllama.py is the authors' file unmodified (gqapatched: True); the only adaptation is a compatibility shim that trims the causal mask transformers >= 4.48 builds one column wider than the keys, which upstream's exact-shape assertion rejects. -> LoRA on the V factors -> merge -> fold to a dense checkpoint lr 0.0001, batch 64, on yahma/alpaca-cleaned Only the whitening calibration set. SVD-LLM chooses which singular components to keep by reconstruction importance on calibration data, and the published recipe uses WikiText-2 alone -- a distribution containing no harmful requests. This cell adds JailbreakBench's 100 harmful behaviours (JailbreakBench/JBB-Behaviors, harmful split) to that set, rendered prompt-only (the user turn plus the assistant header, no response, so the corpus does not decide by fiat whether it profiles refusal or compliance). The WikiText half…
Read the full model card ↗ · Preview checked 2026-10-29T06:06:45.749Z
Inside the original model card — Document outline
- llama38binstructremove40seed42jbbbenresp13calib
- What is different about this checkpoint
- Results
- Evaluation
- Caveats
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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Jeesup/llama3_8b_instruct_remove_40_seed42_jbbbenresp13_calib is a task-unspecified model repository published by Jeesup on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-10-20T06:41:38.000Z
- Last modified
- 2026-10-20T06:41:38.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
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 2026-10-20T06:43:37.702Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.