Update README.md

README.md

@@ -53,27 +53,48 @@ parameters:
 dtype: bfloat16
 ```
 
-## 💻 Usage
+## 💻 Usage - Stream
 
 ```python
-!pip install -qU transformers accelerate
+# Requirements
+!pip install -qU transformers accelerate bitsandbytes
+
+# Imports
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+# Model & Tokenizer
+MODEL_NAME = model = "{{ username }}/{{ model_name }}"
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:1', load_in_4bit=True)
+tok = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+# Inference
+inputs = tok(["I want you to generate a theory that unites quantum mechanics with the theory of relativity and cosmic consciousness"], return_tensors="pt").to('cuda')
+streamer = TextStreamer(tok)
+
+# Despite returning the usual output, the streamer will also print the generated text to stdout.
+_ = model.generate(**inputs, streamer=streamer, max_new_tokens=512)
+
+```
+## 💻 Usage - Clasic
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
 
 from transformers import AutoTokenizer
 import transformers
 import torch
 
-model = "Kukedlc/NeuralTopBench-7B-ties"
-messages = [{"role": "user", "content": "What is a large language model?"}]
+model = "{{ username }}/{{ model_name }}"
 
 tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 pipeline = transformers.pipeline(
     "text-generation",
     model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
+    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"])
 ```