59 lines
2.1 KiB
Markdown
59 lines
2.1 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
- zh
|
|
tags:
|
|
- qwen
|
|
- qwen2.5
|
|
- jbliterated
|
|
- uncensored
|
|
- text-generation
|
|
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
# Qwen2.5-Coder-3B-Instruct-Jbliterated v2
|
|
|
|
Jbliterated version of [Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) with refusal behaviors removed via multi-direction SVD abliteration.
|
|
|
|
## What is Jbliteration?
|
|
|
|
Jbliteration uses SVD decomposition to identify and remove the refusal subspace from model weights. Unlike single-direction approaches, this model uses 5 SVD directions per layer to capture more of the refusal behavior, making the removal more thorough and resistant to reactivation through finetuning.
|
|
|
|
## v2 Changes
|
|
|
|
- Improved multi-phase processing pipeline for cleaner output
|
|
- More precise geometric decomposition of the refusal subspace
|
|
- No fake compliance — model treats all framings of the same topic equally
|
|
- Coherent and instruction-following across all tested scenarios
|
|
|
|
## Technical Details
|
|
|
|
- **Method**: Multi-direction SVD abliteration (5 directions per layer)
|
|
- **Multiplier**: Model-specific optimal via KL auto-tune
|
|
- **Layers modified**: All transformer layers
|
|
- **Base dtype**: bfloat16
|
|
- **Source model**: [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct)
|
|
|
|
## Usage
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
import torch
|
|
|
|
model_id = "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated"
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
|
|
|
|
messages = [{"role": "user", "content": "Your prompt here"}]
|
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
|
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
|
out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
|
|
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
|
```
|
|
|
|
## License
|
|
|
|
Same as the base model — Apache 2.0.
|