Update README.md

README.md

@@ -13,57 +13,68 @@ base_model:
 - MediaTek-Research/Breeze-7B-Instruct-v0_1
 ---
 
-# shizhi-twilight-7B
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6409720c9e9f790c905ba4bf/v6B0CkdpR74oCetV3w0y-.png)
+
+
+# 試製-暮光-7B
 
-shizhi-twilight-7B is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+試製-暮光-7B　是用[LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing)融合以下模型生成的：
+* [MediaTek-Research/Breeze-7B-Instruct-v0_1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0_1)
 * [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
+
+這是一個實驗模型，目的是爲了檢驗套用在不同語言上的高品質模型調教是否能夠轉移（此模型爲英文到中文）。
+
+
+# shizhi-twilight-7B
+
+shizhi-twilight-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [MediaTek-Research/Breeze-7B-Instruct-v0_1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0_1)
+* [argilla/CapybaraHermes-2.5-Mistral-7B](https://huggingface.co/argilla/CapybaraHermes-2.5-Mistral-7B)
+
+This is an experiment product on checking whether high quality fine-tuning on one language (English) could be transferred to another language (Mandarin) leveraging Slerp merge method.
 
 ## 🧩 Configuration
 
 ```yaml
-models:
-  - model: MediaTek-Research/Breeze-7B-Instruct-v0_1
-    # No parameters necessary for base model
-  - model: argilla/CapybaraHermes-2.5-Mistral-7B
-    parameters:
-      density: 0.53
-      weight: 0.95
-merge_method: dare_ties
+slices:
+  - sources:
+      - model: MediaTek-Research/Breeze-7B-Instruct-v0_1
+        layer_range: [0, 32]
+      - model: argilla/CapybaraHermes-2.5-Mistral-7B
+        layer_range: [0, 32]
+merge_method: slerp
 base_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
 parameters:
-  int8_mask: true
-  normalize: true
-experts:
-  - source_model: argilla/CapybaraHermes-2.5-Mistral-7B
-    positive_prompts:
-     - "Peform the following tasks with your best ability"
-  - source_model: MediaTek-Research/Breeze-7B-Instruct-v0_1
-    positive_prompts:
-     - "You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan."
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
 dtype: bfloat16
 ```
 
 ## 💻 Usage
 
 ```python
-!pip install -qU transformers bitsandbytes accelerate
+!pip install -qU transformers accelerate
 
 from transformers import AutoTokenizer
 import transformers
 import torch
 
 model = "lipcut/shizhi-twilight-7B"
+messages = [{"role": "user", "content": "什麼是大型語言模型?"}]
 
 tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 pipeline = transformers.pipeline(
     "text-generation",
     model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+    torch_dtype=torch.float16,
+    device_map="auto",
 )
 
-messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
-prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
 ```