Update README.md on the evaluation parameters (#3139)

Summary:
It's not clear how we got the perplexity numbers. Add the parameters we used to get those numbers.

Pull Request resolved: #3139

Reviewed By: lucylq

Differential Revision: D56319905

Pulled By: iseeyuan

fbshipit-source-id: dc387cc84c2fe7a21e44642ff591000fd6728abb

Author: iseeyuan

examples/models/llama2/README.md

@@ -24,7 +24,7 @@ For Llama3, we can use the same process. Note that it's only supported in the Ex
 ## Quantization:
 We employed 4-bit groupwise per token dynamic quantization of all the linear layers of the model. Dynamic quantization refers to quantizating activations dynamically, such that quantization parameters for activations are calculated, from min/max range, at runtime. Here we quantized activations with 8bits (signed integer). Furthermore, weights are statically quantized. In our case weights were per-channel groupwise quantized with 4bit signed integer. For more information refer to this [page](https://github.com/pytorch-labs/ao/).
 
-We evaluated UncycloText perplexity using [LM Eval](https://github.com/EleutherAI/lm-evaluation-harness). Below are the results for two different groupsizes.
+We evaluated UncycloText perplexity using [LM Eval](https://github.com/EleutherAI/lm-evaluation-harness). Below are the results for two different groupsizes, with max_seq_len 2048, and 1000 samples:
 
 |Llama 2 | Baseline (FP32) | Groupwise 4-bit (128) | Groupwise 4-bit (256)
 |--------|-----------------| ---------------------- | ---------------