Update README.md

README.md

@@ -4,6 +4,7 @@ base_model:
 - ohyeah1/Violet-Lyra-Gutenberg-v2
 - redrix/patricide-12B-Unslop-Mell-v2
 - yamatazen/EtherealAurora-12B-v3
+- yamatazen/EtherealAurora-12B-v2
 tags:
 - merge
 - mergekit
@@ -12,15 +13,34 @@ tags:
 - ohyeah1/Violet-Lyra-Gutenberg-v2
 - redrix/patricide-12B-Unslop-Mell-v2
 - yamatazen/EtherealAurora-12B-v3
+- yamatazen/EtherealAurora-12B-v2
 ---
 
+<img src="./QuasiStarSynth.png" alt="Model Image"/>
+
 # QuasiStarSynth-12B
 
+<b><i>From a time before galaxies settled and stars knew their limits, something titanic burned. 
+<br> Its light was golden, but inside darkness bloomed. 
+<br> A black heart beating beneath layers of radiant fire, devouring slowly, unseen. 
+<br> Neither star nor singularity, this was a monument to scale, a paradox wrapped in brilliance.</i></b>
+
+## 🔧 Recommended Sampling Settings:</b>
+```yaml
+Temperature: 0.75 to 1.25
+Min P: 0.035
+Context Length: Stable at 12k tokens, with possible support for extended contexts
+```
+## 💬 Prompt Format
+Supports ChatML style messages. Example:
+```yaml
+<|im_start|>user
+Your question here.
+<|im_end|>
+<|im_start|>assistant
+```
+
 QuasiStarSynth-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [DreadPoor/Irix-12B-Model_Stock](https://huggingface.co/DreadPoor/Irix-12B-Model_Stock)
-* [ohyeah1/Violet-Lyra-Gutenberg-v2](https://huggingface.co/ohyeah1/Violet-Lyra-Gutenberg-v2)
-* [redrix/patricide-12B-Unslop-Mell-v2](https://huggingface.co/redrix/patricide-12B-Unslop-Mell-v2)
-* [yamatazen/EtherealAurora-12B-v3](https://huggingface.co/yamatazen/EtherealAurora-12B-v3)
 
 ## 🧩 Configuration
 
@@ -85,7 +105,7 @@ from transformers import AutoTokenizer
 import transformers
 import torch
 
-model = "Marcjoni/QuasiStarSynth-12B"
+model = "Marcjoni/AbyssSynth-12B-12B"
 messages = [{"role": "user", "content": "What is a large language model?"}]
 
 tokenizer = AutoTokenizer.from_pretrained(model)
@@ -97,6 +117,6 @@ pipeline = transformers.pipeline(
     device_map="auto",
 )
 
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=1, top_k=0, top_p=1)
 print(outputs[0]["generated_text"])
 ```