Update README.md

README.md

@@ -1,4 +1,13 @@
 ---
+license: other
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+- Open-Orca/SlimOrca-Dedup
+- jondurbin/airoboros-3.2
+- microsoft/orca-math-word-problems-200k
+- m-a-p/Code-Feedback
+- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
+base_model: meta-llama/Meta-Llama-3-8B
 library_name: transformers
 tags:
 - 4-bit
@@ -10,6 +19,17 @@ pipeline_tag: text-generation
 inference: false
 quantized_by: Suparious
 ---
-# 
+# Locutusque/llama-3-neural-chat-v1-8b AWQ
 
-**UPLOAD IN PROGRESS**
+- Model creator: [Locutusque](https://huggingface.co/Locutusque)
+- Original model: [llama-3-neural-chat-v1-8b](https://huggingface.co/Locutusque/llama-3-neural-chat-v1-8b)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6437292ecd93f4c9a34b0d47/6XQuhjWNr6C4RbU9f1k99.png)
+
+## Model Summary
+
+OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
+
+Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
+
+Here, we are finetuning openheremes using DPO with various data meant to  improve its abilities.