float16 conversion

README.md

@@ -0,0 +1,37 @@
+---
+license: other
+datasets:
+- ehartford/wizard_vicuna_70k_unfiltered
+language:
+- en
+tags:
+- uncensored
+---
+
+# Wizard-Vicuna-7B-Uncensored GPTQ
+
+This is a float16 HF repo of [Eric Hartford's 'uncensored' training of Wizard-Vicuna 7B](https://huggingface.co/ehartford/Wizard-Vicuna-7B-Uncensored).
+
+It is the result of converting Eric's float32 repo to float16 for easier storage.
+
+## Repositories available
+
+* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ).
+* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML).
+* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-HF).
+
+# Original model card
+
+This is [wizard-vicuna-13b](https://huggingface.co/junelee/wizard-vicuna-13b) trained against LLaMA-7B with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
+
+Shout out to the open source AI/ML community, and everyone who helped me out.
+
+Note:  
+
+An uncensored model has no guardrails.  
+
+You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
+
+Publishing anything this model generates is the same as publishing it yourself.
+
+You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.