Update README.md

README.md

@@ -5,14 +5,14 @@ tags: []
 
 # Model Card for Model ID
 
-|    Tasks    |Version|Filter|n-shot| Metric |Value |   |Stderr|
-|-------------|------:|------|-----:|--------|-----:|---|-----:|
-|arc_challenge|      1|none  |    25|acc     |0.5691|±  |0.0145|
-|             |       |none  |    25|acc_norm|0.6118|±  |0.0142|
-|truthfulqa_mc2|      2|none  |     0|acc   |0.4239|±  |0.0145|
-|winogrande|      1|none  |     5|acc   |0.7758|±  |0.0117|
-|hellaswag|      1|none  |    10|acc     |0.6310|±  |0.0048|
-|         |       |none  |    10|acc_norm|0.8152|±  |0.0039|
+this model isn't really made for benchmarks, it's worse on everything besides ARC-C and TruthfulQA
+
+| Model                                                        | ARC-C     | HellaSwag | MMLU       | TruthfulQA | Winogrande | GSM8k     |
+| ------------------------------------------------------------ | --------- | --------- | ---------- | ---------- | ---------- | --------- |
+| [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 59.98     | **83.31** | **64.16** | 42.15      | **78.37**  | **37.83** |
+| [crumb/92d52f-ame-full-7B](https://hf.co/crumb/92d52f-ame-full-7B) | **61.18** | 81.52     | 63.44      | **42.39**  | 77.58      | 35.41     |
+
+it's got extra tokens which can all equally be used as masks, you can replace all instances of one token in context with one of the extra tokens (`[f'<ID-{i:06X}>' for i in range(2048)]`) to give the model an extra hard time. it was trained with context length 2048 on three separate replacement techniques through a schedule, with 80% of all sequences being completely replaced with the mask tokens near the end of training.
 
 ## Model Details