Update README.md

README.md

@@ -1,3 +1,42 @@
 ---
 license: llama2
+pipeline_tag: text-generation
+tags:
+- llama
+- llama2
+- not-for-all-audiences
 ---
+# Introduction
+
+Astramix is a merge of various Llama-2-7b finetune models, using [ties-merge method](https://github.com/cg123/ties-merge), thanks for [Chargoddard](https://huggingface.co/chargoddard). 
+Subsequently, lora merge script was used, created by [zarakiquemparte](https://github.com/zarakiquemparte/zaraki-tools) ([link](https://huggingface.co/zarakiquemparte) to the Hugging Face profile.)
+
+Approximate rating for this model, noticed in short-time use:
+* Great roleplay capabilities, limited only by model parameters.
+* Poor quality reasoning, because of the model limitations.
+* Almost censorship absence
+
+Feel free to test the model.
+
+Following base model used for merge: [Llama-2-7B-fp16](https://huggingface.co/TheBloke/Llama-2-7B-fp16)
+
+#### List of models used for merge:
+* [Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b)
+* [airoboros-l2-7b-2.1](https://huggingface.co/jondurbin/airoboros-l2-7b-2.1)
+* [orca_mini_v3_7b ](https://huggingface.co/psmathur/orca_mini_v3_7b)
+* [Platypus2-7B](https://huggingface.co/garage-bAInd/Platypus2-7B)
+* [Tulpar-7b-v0](https://huggingface.co/HyperbeeAI/Tulpar-7b-v0)
+
+Then, two LoRAs was merged into basemix model, using script specified above:
+* [limarp-llama2-v2](https://huggingface.co/lemonilia/limarp-llama2-v2) (Licensed under AGPLv3)
+* [airoboros-lmoe-7b-2.1](https://huggingface.co/jondurbin/airoboros-lmoe-7b-2.1) (Utilizing creative version)
+
+#### I suggest using Alpaca instruct format:
+```
+### Instruction:
+(your instruct prompt is here)
+### Response: {prompt}
+```
+## Limitations and risks
+Llama2 is licensed under LLama 2 Community License, various finetunes or (Q)LoRAs has appropriate licenses depending on used datasets in finetuning or training Low-Rank Adaptations.
+This mix can generate heavily biased output, which aren't suitable for minors or common audience.