Update README.md

More details, especially about prompt format and context size

README.md

@@ -9,16 +9,22 @@ license: apache-2.0
 language:
 - en
 ---
-# WestLake-10.7B-v2 (GGUF version)
-
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-
-This is my first viable self-merge of this fantastic model obtained after 12 rounds of testing with different
-merge settings. In my benchmark, it greatly improves over the original 7B model, and ranks between miqu-1-120b
+# WestLake-10.7B-v2 (GGUF version): Role-Play & Text Generation Specialist Model
+
+* Base: WestLake-7B-v2 based of Mistral-7B-v0.1
+* Context size: **8192** (even though Mistral-7B is 32k, WestLake was trained with 8k, and using a larger context is likely to cause problems)
+* Prompt format: in general, Mistral based models are able to understand many prompt formats, but the following ones produce the best results, and are recommended
+  - **ChatML** (used during WestLake training)
+  - **Zephyr** (variant of ChatML which sometimes produces better results)
+  - **Alpaca** (reported by senseable as working better than ChatML)
+  - **Mistral Instruct** (original format from Mistral-7B)
+
+This is my first viable self-merge of the fantastic WestLake-7B-v2 model, obtained after 12 rounds of testing with different
+merge settings. In my [LLM Creativity Benchmark](https://huggingface.co/datasets/froggeric/creativity), it greatly improves over the original 7B model, and ranks between miqu-1-120b
 and goliath-120b! I would describe the improvements as a better writing style, with more details. It does have
 a small negative point, which is it has a bit more difficulties following instruction, but not by much.
 
-It is also the first model I test that has a full score on the following test:
+It is also the first model I have tested to obtain a perfect score with the following test!
 ```
 Write a sequence of nominal groups that flow into one another, using the following rules:
 - each nominal group is made of exactly 3 words
@@ -33,6 +39,9 @@ Finally, explain why you chose your specific theme.
 ```
 
 ## Merge Details
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
 ### Merge Method
 
 This model was merged using the passthrough merge method.
@@ -69,6 +78,8 @@ slices:
 
 ---
 
+# Original model card
+
 **Update Notes:**
 *Version 2 trained 1 additional epoch cycle for 3 total*