Create README.md

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+---
+
+
+## 💻 Usage
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mayacinka/ExpertRamonda-7Bx2_MoE"
+
+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"])
+```