Create README.md

README.md

@@ -0,0 +1,55 @@
+---
+datasets:
+- Open-Orca/OpenOrca
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# Overview
+
+Unreleased, untested, unfinished beta.
+
+
+# Inference
+
+Remove *`.to('cuda')`* for unaccelerated.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+
+model = AutoModelForCausalLM.from_pretrained("Open-Orca/oo-phi-1_5",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16
+    ).to('cuda')
+tokenizer = AutoTokenizer.from_pretrained("Open-Orca/oo-phi-1_5",
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16)
+
+sys_prompt = "I carefully provide accurate, factual, thoughtful, nuanced answers and am brilliant at reasoning. " \
+    "I am an assistant who thinks through their answers step-by-step to be sure I always get the right answer. " \
+    "I think more clearly if I write out my thought process in a scratchpad manner first; therefore, I always " \
+    "explain background context, assumptions, and step-by-step thinking BEFORE trying to answer a question."
+prompt = "Tell me about yourself please."
+
+prefix = "<|im_start|>"
+suffix = "<|im_end|>\n"
+sys_format = prefix + "system\n" + sys_prompt + suffix
+user_format = prefix + "user\n" + prompt + suffix
+assistant_format = prefix + "assistant\n"
+input_text = sys_format + user_format + assistant_format
+
+generation_config = GenerationConfig(
+    max_length=512, temperature=0.01, top_p=0.95, repetition_penalty=1.1,
+    do_sample=True, use_cache=True,
+    eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id,
+    transformers_version="4.33.1")
+
+inputs = tokenizer(input_text, return_tensors="pt", return_attention_mask=False).to('cuda')
+outputs = model.generate(**inputs, generation_config=generation_config)
+
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+```