Update README.md

README.md

@@ -1,61 +1,36 @@
 ---
 tags:
+- KingNish
+- Power Series
+- llama
+- llama-3
 - merge
 - mergekit
 - lazymergekit
-- KingNish/KingNish-Llama3-8b-v0.2
 base_model:
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
-- KingNish/KingNish-Llama3-8b-v0.2
+- rhysjones/Phi-3-mini-mango-1-llamafied
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
-# Power-Llama-3-14b
+# Power Llama 3 13B Instruct
 
-Power-Llama-3-14b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
-* [KingNish/KingNish-Llama3-8b-v0.2](https://huggingface.co/KingNish/KingNish-Llama3-8b-v0.2)
+Power Llama 3 13B Instruct is a Very Powerful Model under **POWER SERIES**. It's Creativity, Problem Solving skills, Maths and Logic is better than Meta Llama 3 70B and Beats all 13b Models.
 
-## 🧩 Configuration
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6612aedf09f16e7347dfa7e1/3XYEuQ7hXj-dh9abDL2u7.png)
 
-```yaml
-slices:
-- sources:
-  - layer_range: [0, 8]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [4, 12]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [8, 16]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [12, 20]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [16, 24]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [20, 28]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-- sources:
-  - layer_range: [24, 32]
-    model: KingNish/KingNish-Llama3-8b-v0.2
-merge_method: passthrough
-dtype: float16
-```
+## 🧩 Evaluation
+
+Coming Soon
 
 ## 💻 Usage
 
+Same as Llama 3 But
+Best in Creative writing, Logical Reasoning, Translation, Maths, Coding, etc.
+
+## Code
+
 ```python
 !pip install -qU transformers accelerate
 
@@ -63,7 +38,7 @@ from transformers import AutoTokenizer
 import transformers
 import torch
 
-model = "KingNish/Power-Llama-3-14b"
+model = "refine-ai/Power-Llama-3-13b"
 messages = [{"role": "user", "content": "What is a large language model?"}]
 
 tokenizer = AutoTokenizer.from_pretrained(model)
@@ -75,6 +50,6 @@ 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=4096, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
 ```