Update README.md

README.md

@@ -38,7 +38,8 @@ This is the SFT + DPO version of Mixtral Hermes 2, we will also be providing an
     - BigBench
     - TruthfulQA
 3. [Prompt Format](#prompt-format)
-4. [Quantized Models](#quantized-models)
+4. [Inference Example Code](#inference-code)
+5. [Quantized Models](#quantized-models)
 
 ## Benchmark Results
 
@@ -127,6 +128,45 @@ In LM-Studio, simply select the ChatML Prefix on the settings side pane:
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png)
 
+# Inference Code
+
+Here is example code using HuggingFace Transformers to inference the model (note: even in 4bit, it will require more than 24GB of VRAM)
+
+```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, LlamaForCausalLM, MistralForCausalLM
+import bitsandbytes, flash_attn
+
+tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True)
+model = MistralForCausalLM.from_pretrained(
+    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+    torch_dtype=torch.float16,
+    device_map="auto",
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True
+)
+
+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}")
+```  
+
 # Quantized Models:
 
 GGUF: [todo]