ExLlamaV2 Quants
Collection
15 items
•
Updated
Meggido
Meggido
AI & ML interests
7Bs & Alpaca enjoyer.
Focus on LLMs for roleplaying.
Recent Activity
new activity
4 days ago
NarrativAI/CakrawalaRP:Exl2
updated
a collection
11 days ago
ExLlamaV2 Quants
updated
a model
11 days ago
Meggido/Cakrawala-Llama-3.1-8B-6.5bpw-h8-exl2
Organizations
None yet
Meggido's activity
updated
a
collection
11 days ago
updated
a
model
11 days ago
updated
3
models
about 2 months ago
updated
a
collection
about 2 months ago
liked
a
model
2 months ago
liked
a
model
3 months ago
liked
a
dataset
4 months ago
updated
a
collection
5 months ago
updated
a
model
5 months ago
reacted to
grimjim's
post with 🔥
5 months ago
Post
2293
In principle, it's possible to "abliterate" refusals in any Llama 3.1 8B models via application of a LoRA, using only mergekit.
Proof of concept below:
grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
Proof of concept below:
grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
- 5 replies
liked
a
dataset
5 months ago
updated
a
collection
6 months ago
updated
a
model
6 months ago
updated
a
collection
6 months ago
updated
a
model
6 months ago
updated
a
collection
6 months ago
updated
a
model
6 months ago