WizardLM Uncensored is a 13B parameter model based on Llama 2 uncensored by Eric Hartford. The models were trained against LLaMA-7B with a subset of the dataset, responses that contained alignment / …
WizardLM Uncensored is a 13B parameter model based on Llama 2 uncensored by Eric Hartford. The models were trained against LLaMA-7B with a subset of the dataset, responses that contained alignment / moralizing were removed.
## Get started with WizardLM Uncensored
The model used in the example below is the WizardLM Uncensored model, with 13b parameters, which is a general-use model.
### API
1. Start Ollama server (Run `ollama serve`)
2. Run the model
```bash
curl -X POST http://localhost:11434/api/generate -d '{
"model": "wizardlm-uncensored",
"prompt":"Who made Rose promise that she would never let go?"
}'
```
### CLI
1. Install Ollama
2. Open the terminal and run `ollama run wizardlm-uncensored`
Note: The `ollama run` command performs an `ollama pull` if the model is not already downloaded. To download the model without running it, use `ollama pull wizardlm-uncensored`
## Memory requirements
- 13b models generally require at least 16GB of RAM
If you run into issues with higher quantization levels, try using the q4 model or shut down any other programs that are using a lot of memory.
## Model variants
By default, Ollama uses 4-bit quantization. To try other quantization levels, please try the other tags. The number after the q represents the number of bits used for quantization (i.e. q4 means 4-bit quantization). The higher the number, the more accurate the model is, but the slower it runs, and the more memory it requires.
| **Aliases** |
| --- |
| latest, 13b, 13b-llama2, 13b-llama2-q4_0 |
## Model source
**WizardLM Uncensored source on Ollama**
13b parameters source:
[The Bloke](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-Llama2-13B-GGML)
13b parameters original source:
[Eric Hartford](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-Llama2-13b)