Update README.md

README.md

@@ -7,3 +7,35 @@ This model is part of a series of HQQ tests. I make no claims on the performance
 
 This is a very extreme example of quantization.
 
+```python
+# Code to inference Hermes with HF Transformers
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, MixtralForCausalLM
+from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
+import bitsandbytes, flash_attn
+
+tokenizer = AutoTokenizer.from_pretrained('macadeliccc/Nous-Hermes-2-Mixtral-8x7B-DPO-HQQ', trust_remote_code=True)
+model = HQQModelForCasualLM.from_pretrained(
+    "macadeliccc/Nous-Hermes-2-Mixtral-8x7B-DPO-HQQ",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+prompts = [
+    """<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
+<|im_start|>assistant""",
+    ]
+
+for chat in prompts:
+    print(chat)
+    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
+    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
+    print(f"Response: {response}")
+```