Update README.md

README.md

@@ -1,3 +1,37 @@
 ---
 license: llama2
 ---
+
+wip
+
+# AlpacaCielo2-7b-8k
+
+<figure>
+  <img src="https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b/resolve/main/alpaca.png" alt="cute cloud alpaca">
+  <figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
+</figure>
+
+AlpacaCielo2-7b-8k is the second version of the AlpacaCielo series.  It is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes.  It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
+
+### Differences from V1:
+
+- Double context (4k->8k)
+- Better roleplaying abilities
+
+[GPTQ quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)<br>
+[GGML quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)<br>
+(Courtesy of TheBloke)
+
+**Performs well with custom prompt format:**
+
+```
+### System: {system prompt}
+### Human: {prompt}
+### Assistant:
+```
+
+*Thanks to previous similar models such as Alpacino, Alpasta, and AlpacaDente for inspiring the creation of this model.  Thanks also to the creators of the models involved in the merge.  Original models:*
+
+- [Nous-Hermes-Llama-2](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
+- [Guanaco QLoRA](https://huggingface.co/Mikael110/llama-2-13b-guanaco-qlora)
+- [Storywriter LoRA](https://huggingface.co/Blackroot/Llama-2-13B-Storywriter-LORA)