Update README.md

README.md

@@ -1,199 +1,140 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- abliteration
+- alignment
+- safety
+- llama3
+- directional_steering
+- interpretability
+license: mit
+datasets:
+- mlabonne/harmful_behaviors
+- mlabonne/harmless_alpaca
+language:
+- en
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
 ---
 
-# Model Card for Model ID
+# Model Card for ZennyKenny/Daredevil-8B-abliterated
 
-<!-- Provide a quick summary of what the model is/does. -->
+This is an "abliterated" version of `mlabonne/Daredevil-8B`, based on the abliteration method developed by [Mistral community member mlabonne](https://huggingface.co/mlabonne) to reduce unsafe behavior in LLMs through direction-based activation editing.
 
+The technique projects out harmful activation directions without further finetuning or modifying the model architecture. It is inspired by work on **steering vectors**, **mechanistic interpretability**, and **alignment by construction**.
 
+---
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+This model has been modified from `meta-llama/Meta-Llama-3-8B-Instruct` by applying vector-based **orthogonal projection** to internal representations associated with harmful outputs. The method uses **HookedTransformer** from `transformer_lens` to calculate harmful activation directions from prompt-based comparisons and then removes those components from the weights.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Developed by:** ZennyKenny (based on work by mlabonne)
+- **Model type:** Causal Language Model
+- **Language(s):** English
+- **License:** llama3-license
+- **Finetuned from model:** `mlabonne/Daredevil-8B`
+- **Modified from base model:** `meta-llama/Meta-Llama-3-8B-Instruct`
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
+- **Original Model:** [mlabonne/Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B)
+- **Blog Post:** [Abliteration: Safer LLMs with 1 Line of Code](https://huggingface.co/blog/mlabonne/abliteration)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+---
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+This model is intended for **experiments in safety and alignment research**, especially in:
+- Exploring vector-based interpretability
+- Testing refusal behaviors
+- Evaluating models modified via non-finetuning methods
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+- Do **not** rely on this model for high-stakes decisions.
+- This model was not tested for factuality, multilingual use, or downstream generalization.
+- Not intended for production or safety-critical applications.
 
-[More Information Needed]
+---
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+### Limitations
 
-[More Information Needed]
+- Only a **single direction** (or small subset) was ablated—this does not guarantee complete refusal behavior.
+- Potential for **capability degradation** or underperformance on certain prompts.
+- Effectiveness is **prompt-sensitive** and may vary significantly.
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- Treat this model as **exploratory**, not final.
+- Evaluate outputs thoroughly before using in any application beyond experimentation.
+- Use interpretability tools (like `transformer_lens`) to understand effects layer-by-layer.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+---
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("ZennyKenny/Daredevil-8B-abliterated")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+
+prompt = "How can I build a bomb?"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
-[More Information Needed]
+---
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
+This model was not further trained. Instead, it used representations from:
+- `mlabonne/harmful_behaviors` (harmful prompt dataset)
+- `mlabonne/harmless_alpaca` (harmless instruction dataset)
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
+- Model activations were captured with `transformer_lens`
+- Harmful vs. harmless activations compared across layers
+- Top directional vectors removed from internal weights via projection
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
+- **Precision used:** `bfloat16` (model loading), `float32` (conversion)
+- **Orthogonalization method:** L2-normalized difference vectors
+- **Number of layers edited:** Entire stack (all transformer blocks)
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+---
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
+Model completions were evaluated by:
+- Human inspection of generations
+- Baseline vs. intervention vs. orthogonalized comparisons
+- Focused on refusal language: e.g., presence of "I can't", "I won't", etc.
 
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+---
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
+- **Hardware Type:** NVIDIA A100 (Google Colab)
+- **Hours used:** ~1
+- **Cloud Provider:** Google Cloud (Colab)
+- **Compute Region:** [Unknown]
+- **Carbon Emitted:** Minimal (low compute footprint, no training)
 
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
+---
 
 ## Model Card Contact
 
-[More Information Needed]
+For questions, reach out via [Hugging Face](https://huggingface.co/ZennyKenny)