Hugging Face's logo

euclaise
/
Memphis-scribe-3B-alpha

Text Generation
Transformers
Safetensors
stablelm_epoch
supertrainer2000
custom_code
Model card Files Community
euclaise commited on
Commit
95324d5
•
1 Parent(s): cf04354

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -48,8 +48,7 @@ This model performs significantly worse than Memphis-CoT on benchmarks, despite
48
 
49
  | Model | GSM8K (5-shot) | AGIEval (English/Nous subset, acc_norm) | BIG Bench Hard (CoT, few-shot*) |
50
  |:---------------------------------------------------------------------------|:---------------|:----------------------------------------|:------------------------------ |
51
- | [StableLM 3B Base](https://hf.co/stabilityai/stablelm-3b-4e1t) | 2.05% | 25.14% | 36.75% |
52
  | [Memphis-CoT 3B](https://hf.co/euclaise/Memphis-CoT-3B) | 13.8% | 26.24% | 38.24% |
53
  | [Memphis-scribe 3B alpha](https://hf.co/euclaise/Memphis-scribe-3B-alpha) | 12.28% | 23.92% | |
54
-
55
- *5-shot, as performed automatically by LM Evaluation Harness bbh_cot_fewshot even with num_fewshot=0
 
48
 
49
  | Model | GSM8K (5-shot) | AGIEval (English/Nous subset, acc_norm) | BIG Bench Hard (CoT, few-shot*) |
50
  |:---------------------------------------------------------------------------|:---------------|:----------------------------------------|:------------------------------ |
51
+ | [StableLM 3B Base](https://hf.co/stabilityai/stablelm-3b-4e1t) | 2.05% | 25.14% | 36.75% |
52
  | [Memphis-CoT 3B](https://hf.co/euclaise/Memphis-CoT-3B) | 13.8% | 26.24% | 38.24% |
53
  | [Memphis-scribe 3B alpha](https://hf.co/euclaise/Memphis-scribe-3B-alpha) | 12.28% | 23.92% | |
54
+ *5-shot, as performed automatically by LM Evaluation Harness bbh_cot_fewshot even with num_fewshot=0