Create README.md

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+datasets:
+- lodrick-the-lafted/Hermes-100K
+- garage-bAInd/Open-Platypus
+- jondurbin/airoboros-3.2
+---
+
+<img src=https://huggingface.co/lodrick-the-lafted/Grafted-Hermetic-Platypus-B-2x7B/resolve/main/ghp.png>
+
+# Grafted-Hermetic-Platypus-B-2x7B
+
+MoE merge of
+- [Platyboros-Instruct-7B](https://huggingface.co/lodrick-the-lafted/Platyboros-Instruct-7B) 
+- [Hermes-Instruct-7B-100K](https://huggingface.co/lodrick-the-lafted/Hermes-Instruct-7B-100K)
+
+<br />
+<br />
+
+# Prompt Format
+
+Both the default Mistral-Instruct tags and Alpaca are fine, so either:
+```
+<s>[INST] {sys_prompt} {instruction} [/INST] 
+```
+
+or
+
+
+```
+{sys_prompt}
+
+### Instruction:
+{instruction}
+
+### Response:
+
+```
+The tokenizer default is Alpaca this time around.
+
+<br />
+<br />
+
+# Usage
+
+```python
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "lodrick-the-lafted/Grafted-Hermetic-Platypus-A-2x7B"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+)
+
+messages = [{"role": "user", "content": "Give me a cooking recipe for an orange pie."}]
+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_p=0.95)
+print(outputs[0]["generated_text"])
+```
+