Update README.md

README.md

@@ -42,13 +42,39 @@ pipeline_tag: text-generation
 
 <h2>Llama-3.2-1B-Instruct-NEO-SI-FI-GGUF</h2>
 
-It is the new "Llama-3.2-1B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Science Fictions and Story dataset.
+It is the new "Llama-3.2-1B-Instruct", max context of 131,000 (128k) with the NEO IMATRIX Science Fiction and Story dataset.
+
+The power in this 1B (for its size) is frankly jaw dropping.
 
 This model IS bullet proof and operates with all parameters, including temp settings from 0 to 5. 
 
-The NEO IMATRIX dataset V2 was applied to it to enhance creativity.
+The NEO IMATRIX dataset V2 was applied to it to enhance creativity. (see examples below)
+
+<B>Model Template:</B>
+
+This is a LLAMA3 model, and requires Llama3 template, but may work with other template(s) and has maximum context of 8k / 8192. 
+However this can be extended using "rope" settings up to 32k.
 
-This model requires Llama3 template.
+If you use "Command-R" template your output will be very different from using "Llama3" template.
+
+Here is the standard LLAMA3 template:
+
+<PRE>
+{
+  "name": "Llama 3",
+  "inference_params": {
+    "input_prefix": "<|start_header_id|>user<|end_header_id|>\n\n",
+    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
+    "pre_prompt": "You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.",
+    "pre_prompt_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
+    "pre_prompt_suffix": "<|eot_id|>",
+    "antiprompt": [
+      "<|start_header_id|>",
+      "<|eot_id|>"
+    ]
+  }
+}
+</PRE>
 
 Please refer to the original model card for this model from Meta-Llama for additional details on operation.
 
@@ -97,6 +123,4 @@ This enhancement WAS NOT used to generate the examples below.
 <B>
 Example generations at TEMP = .8, IQ4_XS, REP PEN 1.1
 
-</B>
-
-
+</B>