Update README.md

README.md

@@ -3,52 +3,80 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-- not-for-all-audiences
 - llama-cpp
 - gguf-my-repo
-base_model: v000000/MysticGem-v1.3-L2-13B
+- not-for-all-audiences
+- llama
+base_model: v000000/l2-test-001
 ---
 
+# MysticGem-v1.3-L2-13B l2-test-001
+
+RP Model, pretty good result!
+
+Probably final. Smart, novel, lewd etc etc.
+
+### Rank no.1 chaiverse for 13B
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/lKzERgJPnOxxzWsGJ-86M.png)
+
 # v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF
 This model was converted to GGUF format from [`v000000/MysticGem-v1.3-L2-13B`](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/v000000/MysticGem-v1.3-L2-13B) for more details on the model.
 
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+# merge
 
-```bash
-brew install llama.cpp
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-```
-Invoke the llama.cpp server or the CLI.
+## Merge Details
+### Merge Method
 
-### CLI:
-```bash
-llama --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -p "The meaning to life and the universe is"
-```
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
 
-### Server:
-```bash
-llama-server --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -c 2048
-```
+### Models Merged
 
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+The following models were included in the merge:
+* [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3)
+* [Locutusque/Orca-2-13b-SFT-v4](https://huggingface.co/Locutusque/Orca-2-13b-SFT-v4)
+* [Sao10K/Stheno-Inverted-1.2-L2-13B](https://huggingface.co/Sao10K/Stheno-Inverted-1.2-L2-13B)
+* [Walmart-the-bag/MysticFusion-13B](https://huggingface.co/Walmart-the-bag/MysticFusion-13B)
+* [Undi95/Amethyst-13B](https://huggingface.co/Undi95/Amethyst-13B)
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+### Configuration
 
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-```
-cd llama.cpp && LLAMA_CURL=1 make
-```
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Undi95/Amethyst-13B
+    parameters:
+      weight: 0.3
+  - model: Walmart-the-bag/MysticFusion-13B
+    parameters:
+      weight: 0.35
+  - model: Sao10K/Stheno-Inverted-1.2-L2-13B
+    parameters:
+      weight: 0.15
+  - model: KoboldAI/LLaMA2-13B-Erebus-v3
+    parameters:
+      weight: 0.1
+  - model: Locutusque/Orca-2-13b-SFT-v4
+    parameters:
+      weight: 0.1
+merge_method: linear
+dtype: bfloat16
 
-Step 3: Run inference through the main binary.
-```
-./main --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -p "The meaning to life and the universe is"
-```
-or 
 ```
-./server --hf-repo v000000/MysticGem-v1.3-L2-13B-Q4_K_M-GGUF --hf-file mysticgem-v1.3-l2-13b-q4_k_m.gguf -c 2048
+
+### Prompt Format (Alpaca):
+```bash
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+Take the role of {{char}} in a play where you leave a lasting impression on {{user}}. Never skip or gloss over {{char}}'s actions.
+
+### Instruction:
+{prompt}
+### Response:
+{output}
 ```