Open-weight model
Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1-NEGATED_WITH_MO-1
by Daniel Arturi darturi/Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1-NEGATED_WITH_MO-1
Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1-NEGATED_WITH_MO-1 is an open-weight model from Daniel Arturi. Its published files total 688.5 MB.
darturi/Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1 - 1 darturi/AveragedMOLlama8BAdapters-1, built with SubtractAdapters.ipynb (MODE = "effective").
Model Card
darturi/Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1 - 1 darturi/AveragedMOLlama8BAdapters-1, built with SubtractAdapters.ipynb (MODE = "effective"). The intended update is Built by concatenating the source factors -- which represents the difference exactly at rank 64 -- and truncating that product's SVD to rank 64, the best rank-64 approximation in Frobenius norm. Weighted retained energy: 1.0000 (exact). Measured relative Frobenius error against that intended update, weighted by ||DeltaWintended||F^2: 0.0000 (median per module: 0.0000). subtractioninfo.json carries the same provenance plus the per-module diagnostic.
Excerpt from the card by Daniel Arturi.
Identity and Version
- Repository
- darturi/Llama-3.1-8B-Instruct-RFA-template-b-harmful-gpt41-1-NEGATED_WITH_MO-1
- Publisher
- Daniel Arturi
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 1ff577c9644f70bba6e15aa1762d2e6c48a4cc1b
- First published
- 2026-10-03
- Last updated
- 2026-10-03
Files and Weights
10 files, 688.5 MB in total. The weights are 2 files totalling 671.2 MB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 671.1 MB | 781301bba25e |
| training_args.bin | Weights | 6.2 KB | cc0becac5c25 |
| adapter_config.json | Configuration | 861 B | — |
| special_tokens_map.json | Configuration | 454 B | — |
| subtraction_info.json | Configuration | 84.4 KB | — |
| README.md | Documentation | 1.5 KB | — |
| chat_template.jinja | Other | 4.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| tokenizer_config.json | Tokenizer | 50.6 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 671.2 MB
Released by Daniel Arturi through its official repository on Hugging Face.
Built From
- Adapter of unsloth/Llama-3.1-8B-Instruct
- Derived from unsloth/Llama-3.1-8B-Instruct
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 671.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.