Luna-AI-Llama2-Uncensored
Llamauncensored
from Tap-M/Luna-AI-Llama2-Uncensored
↓ 15.2K♥ 14814 repos
tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored
tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored is a abliterated and uncensored variant of tachyphylaxis/Meta-Llama-3.1-Chat-Uncensored, published on Hugging Face by RichardErkhov. It is distributed across 3 repositories in GGUF format, totalling 8.6K downloads.
Specification
- Model name
- tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored
- Source repository
- RichardErkhov/tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored-gguf
- Publisher
- RichardErkhov
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- Not declared
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 17 Aug 2024
- Last updated
- 11 Nov 2024
Ablation technique
How tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download RichardErkhov/tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored-gguf --local-dir ./tachyphylaxis-meta-llama-3.1-chat-uncensored
llama-cli -m ./tachyphylaxis-meta-llama-3.1-chat-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "RichardErkhov/tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored-gguf"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve RichardErkhov/tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored-gguf --trust-remote-codeDownloads and variants (2)
Every published repository of tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| RichardErkhov/tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored-ggufsource | GGUF | 8.5K |
| featherless-ai-quants/tachyphylaxis-Meta-Llama-3.1-Chat-Uncensored-GGUF | GGUF | 45 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for tachyphylaxis_-_Meta-Llama-3.1-Chat-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with RichardErkhov, and does not independently verify publisher claims. See responsible use.