Downloads · 30 days
500
1% of all-time downloads
grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF
Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF is a text generation model from grimjim. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.1.
This repo contains select GGUF quants of a model that is a merge of pre-trained language models created using mergekit.
Downloads · 30 days
500
1% of all-time downloads
All-time downloads
44K
Public
Repo size
34.3 GB
Likes
31
Public
Click a slice to open those files.
.gguf25.8 GB · 100%
From the Hugging Face model README
This repo contains select GGUF quants of a model that is a merge of pre-trained language models created using mergekit.
A LoRA was applied to "abliterate" refusals in meta-llama/Meta-Llama-3.1-8B-Instruct. The result appears to work despite the LoRA having been derived from Llama 3 instead of Llama 3.1, which implies that there is significant feature commonality between the 3 and 3.1 models.
The LoRA was extracted from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 and uses meta-llama/Meta-Llama-3-8B-Instruct as a base.
Built with Llama.
This model was merged using the task arithmetic merge method using meta-llama/Meta-Llama-3.1-8B-Instruct + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.
The following YAML configuration was used to produce this model:
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
merge_method: task_arithmetic
parameters:
normalize: false
slices:
- sources:
- layer_range: [0, 32]
model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
weight: 1.0