Create README.md

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- yanolja/KoSOLAR-10.7B-v0.2
+- yanolja/Bookworm-10.7B-v0.4-DPO
+base_model:
+- yanolja/KoSOLAR-10.7B-v0.2
+- yanolja/Bookworm-10.7B-v0.4-DPO
+---
+
+# solar_merge_test_1
+
+## 🧩 Configuration
+
+```yaml
+base_model: yanolja/KoSOLAR-10.7B-v0.2
+dtype: float16
+experts:
+  - source_model: yanolja/KoSOLAR-10.7B-v0.2
+    positive_prompts: ["당신은 사람들에게 도움을 주는 어시스턴트이다."]
+  - source_model: yanolja/Bookworm-10.7B-v0.4-DPO
+    positive_prompts: ["당신은 다방면으로 답변을 잘하는 어시스턴트이다."]
+gate_mode: cheap_embed
+tokenizer_source: base
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jieunhan/solar_merge_test_3"
+
+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"])
+```