georgesung
/

open_llama_7b_qlora_uncensored

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

georgesung commited on Mar 7

Commit

d31d867

•

1 Parent(s): 84a5970

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -1,12 +1,12 @@
 ---
 license: apache-2.0
 datasets:
-- ehartford/wizard_vicuna_70k_unfiltered
 base_model: OpenLLaMA-7B
 ---
 # Overview
-Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered).
 Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance, took ~18 hours to train.
 # Prompt style

 ---
 license: apache-2.0
 datasets:
+- georgesung/wizard_vicuna_70k_unfiltered
 base_model: OpenLLaMA-7B
 ---
 # Overview
+Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset (originally from [ehartford/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)).
 Used QLoRA for fine-tuning. Trained for one epoch on a 24GB GPU (NVIDIA A10G) instance, took ~18 hours to train.
 # Prompt style