Update README.md

README.md

@@ -25,6 +25,14 @@ It achieves the following results on the evaluation set:
 - Logits/rejected: -2.5535
 - Logits/chosen: -2.7973
 
+
+```
+hf (pretrained=fblgit/juanako-7b-v1,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 3, batch_size: 4
+```
+|Tasks|Version|  Filter  |  Metric   |Value |   |Stderr|
+|-----|-------|----------|-----------|-----:|---|-----:|
+|gsm8k|Yaml   |get-answer|exact_match|0.4556|±  |0.0137|
+
 ## Model description
 
 **It seems to outperforms the original Zephyr in most of the tasks.**
@@ -46,6 +54,15 @@ Research purposes.
 alignment-handbook DPO with UNA on top of the SFT lora.
 
 ### Evaluation lm-evaluation-harness
+
+#### GSM8K
+```
+hf (pretrained=/root/juanako-7b-v1-beta,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 3, batch_size: 4
+```
+|Tasks|Version|  Filter  |  Metric   |Value |   |Stderr|
+|-----|-------|----------|-----------|-----:|---|-----:|
+|gsm8k|Yaml   |get-answer|exact_match|0.4556|±  |0.0137|
+
 #### 0-Shot
 ```
 hf (pretrained=fblgit/juanako-7b-v1,load_in_4bit=False,dtype=float16), limit: None, num_fewshot: 0, batch_size: 8