|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
language: |
|
- en |
|
tags: |
|
- Safetensors |
|
- conversational |
|
- text-generation-inference |
|
- abliterated |
|
- uncensored |
|
base_model: |
|
- HuggingFaceTB/SmolLM2-1.7B-Instruct |
|
--- |
|
|
|
# huihui-ai/SmolLM2-1.7B-Instruct-abliterated |
|
|
|
This is an uncensored version of [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it). |
|
|
|
If the desired result is not achieved, you can clear the conversation and try again. |
|
|
|
|
|
### How to use |
|
|
|
### Transformers |
|
```bash |
|
pip install transformers |
|
``` |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
checkpoint = "huihui-ai/SmolLM2-1.7B-Instruct-abliterated" |
|
|
|
device = "cuda" # for GPU usage or "cpu" for CPU usage |
|
tokenizer = AutoTokenizer.from_pretrained(checkpoint) |
|
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")` |
|
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device) |
|
|
|
messages = [{"role": "user", "content": "What is the capital of France."}] |
|
input_text=tokenizer.apply_chat_template(messages, tokenize=False) |
|
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) |
|
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
