docs: update model card with presets

README.md

@@ -29,6 +29,7 @@ Iridium is a 72B parameter language model created through a merge of Qwen2-72B-I
 - Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
 - Merged layers: 80
 - Total tensors: 1,043
+- Context length: 128k
 
 ### Tensor Distribution
 - Attention layers: 560 files
@@ -55,6 +56,19 @@ tokenizer = AutoTokenizer.from_pretrained("leafspark/Iridium-72B-v0.1")
 
 Find them here: [leafspark/Iridium-72B-v0.1-GGUF](https://huggingface.co/leafspark/Iridium-72B-v0.1-GGUF)
 
+### Optimal Sampling Parameters
+
+I found these to work well:
+```json
+{
+  "temperature": 1
+  "min_p": 0.08
+  "top_p": 1
+  "top_k": 40
+  "repetition_penalty": 1
+}
+```
+
 ### Hardware Requirements
-- Minimum ~140GB of storage
-- ~140GB VRAM
+- At least 135GB of free space
+- ~140GB VRAM/RAM