Update README.md

README.md

@@ -1,3 +1,93 @@
----
-license: cc-by-nc-4.0
----
+---
+base_model:
+- NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
+- rombodawg/Open_Gpt4_8x7B_v0.2
+- mistralai/Mixtral-8x7B-Instruct-v0.1
+tags:
+- mergekit
+- merge
+- not-for-all-audiences
+- nsfw
+- mixtral
+license: cc-by-nc-4.0
+---
+
+<!-- description start -->
+My Exllamav2 3.75 bpw quantization of [NoromaidxOpenGPT4-2](https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-2), quantized with default calibration dataset. Included is measurement json, so you can do your own quants.
+> [!IMPORTANT]
+>This bpw is the perfect size for 24GB cards, and can fit 32k context. Make sure to enable 4-bit cache option.
+
+>[!NOTE]
+> This model is great for rp and I recommend using the Alpaca presets in SillyTavern.
+
+## Original Card
+## Description
+
+This repo contains fp16 files of NoromaidxOpenGPT4-2.
+
+The model was created by merging Noromaid-8x7b-Instruct with Open_Gpt4_8x7B_v0.2 the exact same way [Rombodawg](https://huggingface.co/rombodawg) done his merge.
+
+The only difference between [NoromaidxOpenGPT4-1](https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-1/) and [NoromaidxOpenGPT4-2](https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-2/) is that the first iteration use Mixtral-8x7B as a base for the merge (f16), where the second use Open_Gpt4_8x7B_v0.2 as a base (bf16).
+
+After further testing and usage, the two model was released, because they each have their own qualities.
+
+You can download the imatrix file to do many other quant [HERE](https://huggingface.co/NeverSleep/NoromaidxOpenGPT4-2/blob/main/imatrix-2.dat).
+<!-- description end -->
+<!-- prompt-template start -->
+### Prompt template:
+
+## Alpaca
+
+```
+### Instruction:
+{system prompt}
+
+### Input:
+{prompt}
+
+### Response:
+{output}
+```
+
+## Mistral
+
+```
+[INST] {prompt} [/INST] 
+```
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [rombodawg/Open_Gpt4_8x7B_v0.2](https://huggingface.co/rombodawg/Open_Gpt4_8x7B_v0.2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3)
+* [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: mistralai/Mixtral-8x7B-Instruct-v0.1
+    parameters:
+      density: .5
+      weight: 1
+  - model: NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
+    parameters:
+      density: .5
+      weight: .7
+merge_method: ties
+base_model: rombodawg/Open_Gpt4_8x7B_v0.2
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+```
+
+### Support
+
+If you want to support us, you can [here](https://ko-fi.com/undiai).