Update README.md

README.md

@@ -12,11 +12,12 @@ This repo contains the Base (completed pretrain cudalm checkpoint) variant of LS
  - T1 sidecar: 48KB
  - Environment vars: 295B
 
-# LS-Micro-Base: Smallest and fastest model in the LS family.
+# LS-Micro: Smallest and fastest model in the LS family.
 
 |               | HellaSwag | ARC-E | ARC-C | PIQA     | LAMBADA | ArithMark | II*  |
 | ------------- | --------- | ----- | ----- | -------- | ------- | --------- | ---- |
 | LS-Micro-Base | 27.41     | 34.72 | 21.93 | 54.84    | 11.06   | 35.50     | 7.24 |
+| LS-Micro-CPT  | 26.84     | 34.22 | 21.93 | 55.28    | 9.94    | 35.70     | 7.23 |
 | LS-Tiny-Base  | 27.11     | 32.24 | 24.49 | 53.81    | 2.99    | 34.00     | 6.22 |
 
 LS-Micro is 3x smaller than LS-TIny (11M vs 31M), and has 3x less active parameters (5M vs 15M), yet has a 16% higher intelligence index.
@@ -51,21 +52,9 @@ Multiple choice:
 | relevance     | 20  | 5.0%      | 30.0%       | 25.0%  |
 | consistency   | 18  | 61.1%     | 72.2%       | 25.0%  |
 | arithmetic    | 15  | 46.7%     | 46.7%       | 25.0%  |
-| ALL: LS-Micro | 118 | **46.6%** | **52.5%**   | 25.0%  |
-| ALL: LS-Tiny  | 118 | 40.7%     | 47.5%       | 25.0%  |
-
-Open ended generation:
-| category | n  | eot    | kw    | degen | rel/tok | relwin |
-| -------- | -- | ------ | ----- | ----- | ------- | ------ |
-| greet    | 8  | 75.0%  | 62.5% | 12.5% | +0.428  | 100.0% |
-| explain  | 16 | 62.5%  | 75.0% | 6.2%  | +0.624  | 100.0% |
-| advice   | 16 | 37.5%  | 68.8% | 6.2%  | +0.436  | 100.0% |
-| creative | 16 | 62.5%  | 93.8% | 0.0%  | +0.925  | 100.0% |
-| list     | 16 | 68.8%  | 43.8% | 6.2%  | +0.806  | 100.0% |
-| howto    | 12 | 25.0%  | 58.3% | 8.3%  | +0.334  | 100.0% |
-| opinion  | 8  | 75.0%  | 62.5% | 0.0%  | +1.104  | 100.0% |
-| math     | 4  | 100.0% | 0.0%  | 0.0%  | +2.438  | 100.0% |
-| ALL      | 96 | 58.3%  | 64.6% | 5.2%  | +0.736  | 100.0% |
+| LS-Micro-Base | 118 | **46.6%** | **52.5%**   | 25.0%  |
+| LS-Micro-CPT  | 118 | 37.3%     | 40.7%       | 25.0%  |
+| LS-Tiny-Base  | 118 | 40.7%     | 47.5%       | 25.0%  |
 
 ## The base model is horrendous at chat, and is intended to be used as a base to be finetuned for specialised tasks. 
 To try LS-Micro or to train/finetune the model, follow this quickstart guide: