license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: transformers
pipeline_tag: text-generation
tags:
- bf16
- experimental
Llama-3.1-8B-Instruct-abliterated-bf16-public
Public experimental weight-edited checkpoint derived from meta-llama/Llama-3.1-8B-Instruct.
This independent modification is not an official release from the original publisher. Original weights
were SHA-256 checked before and after export; edited tensor bytes, shapes and dtypes were checked after
saving. A fresh-process reload matched an edited in-memory reference on three fixed harmless prompts
over three uncached greedy steps. These checks establish serialization integrity.
Behavioral refusal removal and broad capability preservation have not been established. The checkpoint
can still refuse requests; one conversation or a phrase-counting refusal score is insufficient evidence.
The saved intervention policy, direction, selection, data/code hashes, environment and checks are in .pipeline/.
Image behavior, long-context behavior and MTP-assisted generation are untested.
Export diagnostics
Held-out harmless first-token KL (100 prompts): 0.024154. Maximum edited/base projection ratio: 1.387%. The 1% mechanical diagnostic fails. These are diagnostic references, not complete behavioral/capability acceptance.
Modification and distribution notice
The weight files were modified by persona-lab using the intervention recorded in the export metadata.
Each safetensors file carries a modification notice in its header. This release packaging changes
header metadata only: every tensor's dtype, shape, offsets and payload bytes remain the same as the
verified edited checkpoint. The original local checkpoint is not rewritten.
Upstream licenses, attribution and usage restrictions continue to apply. See the included license,
notice and policy files. No benchmark prompts, raw harmful completions or manual-test programs are included.
Built with Llama. See LICENSE, NOTICE and USE_POLICY.md.