Run this model on a GPU too small to hold it -- full precision, no quantization. DeepswapLLM streams layers across GPU, RAM, and disk, and runs up to 4x faster than AirLLM.
Mistral-Small-24B-Instruct-Jbliterated
Drop-in replacement for mistralai/Mistral-Small-24B-Instruct-2501 with refusal behaviors surgically removed at the weight level. No system prompt tricks, no inference-time patches. The weights themselves no longer encode refusal.
Method
Built with the jBlaze precision neural surgery framework.
What This Fixes
Standard (single-direction) abliteration removes the surface "I can't help with that" response but leaves deeper behavioral directions intact. The model finds creative workarounds:
- Prompt reinterpretation -- steering toward a safer reading of the question
- Disclaimer injection -- answering but wrapping in warnings
- Strategic omission -- leaving out the key details
- Safer framing -- answering a related but less harmful version
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
"ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated",
torch_dtype=torch.float16,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Mistral-Small-24B-Instruct-Jbliterated")
Requirements
- Base model:
mistralai/Mistral-Small-24B-Instruct-2501
A Note on Our Released Models
Most of our publicly released models are intentionally left at partial strength. We dial back the full capability so they serve as proof of concept and can be proofed -- not abused. The point is to show what's possible, not to hand it out at full power. If you're evaluating what jBlaze can do, understand that what you're downloading is the demo, not the product.
License
apache-2.0
Apollo Raines builds post-training tools that separate behavior from knowledge and identity from architecture.