Update README.md

README.md

@@ -1,67 +1,7 @@
 ---
 license: apache-2.0
-tags:
-- moe
-- frankenmoe
-- merge
-- mergekit
-- lazymergekit
-- yanolja/EEVE-Korean-10.8B-v1.0
-- upstage/SOLAR-10.7B-v1.0
 base_model:
 - yanolja/EEVE-Korean-10.8B-v1.0
 - upstage/SOLAR-10.7B-v1.0
 ---
-
-# TEST_MODEL
-
-TEST_MODEL is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0)
-* [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
-
-## 🧩 Configuration
-
-```yaml
-base_model: yanolja/EEVE-Korean-10.8B-v1.0
-dtype: float16
-experts:
-  - source_model: yanolja/EEVE-Korean-10.8B-v1.0
-    positive_prompts: ["You are an helpful general-pupose assistant."]
-  - source_model: upstage/SOLAR-10.7B-v1.0
-    positive_prompts: ["You are helpful assistant."]
-merge_method: slerp
-gate_mode: cheap_embed
-parameters:
-  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
-
-tokenizer_source: base
-```
-
-## 💻 Usage
-
-```python
-!pip install -qU transformers bitsandbytes accelerate
-
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "jieunhan/TEST_MODEL"
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
-)
-
-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"])
-```
+TESTING