Update README.md

README.md

@@ -34,7 +34,7 @@ This optimization reduces the number of bits per parameter from 16 to 8, reducin
 Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-tensor quantization is applied, in which a single linear scaling maps the FP8 representations of the quantized weights and activations.
 [AutoFP8](https://github.com/neuralmagic/AutoFP8) is used for quantization with 512 sequences of UltraChat.
 
-<!-- ## Deployment
+## Deployment
 
 ### Use with vLLM
 
@@ -46,7 +46,7 @@ from transformers import AutoTokenizer
 
 model_id = "neuralmagic/Mistral-Nemo-Instruct-2407-FP8"
 
-sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)
+sampling_params = SamplingParams(temperature=0.3, top_p=0.9, max_tokens=256)
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
@@ -57,7 +57,7 @@ messages = [
 
 prompts = tokenizer.apply_chat_template(messages, tokenize=False)
 
-llm = LLM(model=model_id)
+llm = LLM(model=model_id, max_model_len=4096)
 
 outputs = llm.generate(prompts, sampling_params)
 
@@ -65,7 +65,7 @@ generated_text = outputs[0].outputs[0].text
 print(generated_text)
 ```
 
-vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. -->
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
 
 ## Creation